Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4905 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.6677. Min Act: -0.1700
Data Index: 2527602 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.6677. Min Act: -0.1700
Data Index: 8521394 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.5427. Min Act: -0.1700
Data Index: 6945969 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.6052. Min Act: -0.1700
Data Index: 3213010 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.4802. Min Act: -0.1700
Data Index: 1354936 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.4802. Min Act: -0.1700
Data Index: 4466907 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.4802. Min Act: -0.1700
Data Index: 1699687 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.4177. Min Act: -0.1700
Data Index: 5203955 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.3552. Min Act: -0.1700
Data Index: 5811371 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.3552. Min Act: -0.1700
Data Index: 3646497 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.3552. Min Act: -0.1700
Data Index: 2356224 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.2927. Min Act: -0.1700
Data Index: 6928197 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.2927. Min Act: -0.1700
Data Index: 2879294 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.2927. Min Act: -0.1700
Data Index: 5160708 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.2927. Min Act: -0.1700
Data Index: 3714520 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.2927. Min Act: -0.1700
Data Index: 7631892 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.2927. Min Act: -0.1700
Data Index: 7304084 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.2302. Min Act: -0.1700
Data Index: 1024819 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.2302. Min Act: -0.1700
Data Index: 985035 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6677. Min Range: -7.6677
Max Act: 7.2302. Min Act: -0.1700
Data Index: 4494160 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19