Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2431 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.6405. Min Act: -0.1700
Data Index: 7195285 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.5780. Min Act: -0.1700
Data Index: 5654274 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.5155. Min Act: -0.1700
Data Index: 2623924 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.4530. Min Act: -0.1700
Data Index: 1919663 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.4530. Min Act: -0.1700
Data Index: 3391874 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.4530. Min Act: -0.1700
Data Index: 2175796 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.4530. Min Act: -0.1700
Data Index: 4668942 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.3905. Min Act: -0.1700
Data Index: 8289808 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.3905. Min Act: -0.1700
Data Index: 3461313 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.3280. Min Act: -0.1700
Data Index: 5788471 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.3280. Min Act: -0.1700
Data Index: 7970772 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.2655. Min Act: -0.1700
Data Index: 81060 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.3280. Min Act: -0.1700
Data Index: 3832511 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.3280. Min Act: -0.1700
Data Index: 4362741 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.3280. Min Act: -0.1700
Data Index: 4101936 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.3280. Min Act: -0.1700
Data Index: 7672059 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.2655. Min Act: -0.1700
Data Index: 4362743 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.2655. Min Act: -0.1700
Data Index: 3401013 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.2030. Min Act: -0.1700
Data Index: 6285440 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6405. Min Range: -11.6405
Max Act: 11.2655. Min Act: -0.1700
Data Index: 4362739 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19