Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4407 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.8872. Min Act: -0.1700
Data Index: 2878127 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.3560. Min Act: -0.1700
Data Index: 8510631 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.3872. Min Act: -0.1700
Data Index: 7313867 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.3872. Min Act: -0.1700
Data Index: 8571606 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.2622. Min Act: -0.1700
Data Index: 8641340 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.2622. Min Act: -0.1700
Data Index: 5190102 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.2310. Min Act: -0.1700
Data Index: 3621699 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.2310. Min Act: -0.1700
Data Index: 8678422 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.2310. Min Act: -0.1700
Data Index: 6520772 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.1685. Min Act: -0.1700
Data Index: 6970024 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.1997. Min Act: -0.1700
Data Index: 3897016 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.1060. Min Act: -0.1700
Data Index: 7754 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.1372. Min Act: -0.1700
Data Index: 6247296 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.0747. Min Act: -0.1700
Data Index: 879050 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.0747. Min Act: -0.1700
Data Index: 1820759 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.0122. Min Act: -0.1700
Data Index: 4630355 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8872. Min Range: -7.8872
Max Act: 7.0435. Min Act: -0.1700
Data Index: 7142885 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8872. Min Range: -7.8872
Max Act: 6.9497. Min Act: -0.1700
Data Index: 8575626 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8872. Min Range: -7.8872
Max Act: 6.9810. Min Act: -0.1700
Data Index: 2786497 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8872. Min Range: -7.8872
Max Act: 6.9810. Min Act: -0.1700
Data Index: 1566346 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19