Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4240 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2897. Min Range: -8.2897
Max Act: 8.2897. Min Act: -0.1700
Data Index: 2811322 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.9460. Min Act: -0.1700
Data Index: 5501099 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.7897. Min Act: -0.1700
Data Index: 2811321 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.7897. Min Act: -0.1700
Data Index: 895728 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.7585. Min Act: -0.1700
Data Index: 4733903 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.6022. Min Act: -0.1700
Data Index: 341612 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.6022. Min Act: -0.1700
Data Index: 2304425 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.6022. Min Act: -0.1700
Data Index: 5318927 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.5710. Min Act: -0.1700
Data Index: 7308080 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.5710. Min Act: -0.1700
Data Index: 1000002 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.6022. Min Act: -0.1700
Data Index: 5810352 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.5397. Min Act: -0.1700
Data Index: 8375138 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.5085. Min Act: -0.1700
Data Index: 4847246 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.4460. Min Act: -0.1700
Data Index: 1854556 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.4772. Min Act: -0.1700
Data Index: 7817303 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.4460. Min Act: -0.1700
Data Index: 5131423 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.4460. Min Act: -0.1700
Data Index: 7427291 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.4460. Min Act: -0.1700
Data Index: 5669547 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.4147. Min Act: -0.1700
Data Index: 2811324 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2897. Min Range: -8.2897
Max Act: 7.4147. Min Act: -0.1700
Data Index: 3225341 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19