Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.5092. Min Act: -0.1700
Data Index: 4368532 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4779. Min Act: -0.1700
Data Index: 8301067 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4466. Min Act: -0.1700
Data Index: 5592773 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4466. Min Act: -0.1700
Data Index: 6947916 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4466. Min Act: -0.1700
Data Index: 854158 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4152. Min Act: -0.1700
Data Index: 4229634 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4152. Min Act: -0.1700
Data Index: 4292179 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4152. Min Act: -0.1700
Data Index: 854157 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4152. Min Act: -0.1700
Data Index: 4494514 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4152. Min Act: -0.1700
Data Index: 8411161 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4152. Min Act: -0.1700
Data Index: 1622629 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.4152. Min Act: -0.1700
Data Index: 6502587 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.3839. Min Act: -0.1700
Data Index: 2526141 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.3839. Min Act: -0.1700
Data Index: 4217673 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.3839. Min Act: -0.1700
Data Index: 2864357 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.3839. Min Act: -0.1700
Data Index: 4231714 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.3839. Min Act: -0.1700
Data Index: 3178707 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.3839. Min Act: -0.1700
Data Index: 4397159 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.3839. Min Act: -0.1700
Data Index: 3448033 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5092. Min Range: -3.5092
Max Act: 3.3839. Min Act: -0.1700
Data Index: 3448035 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19