Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.9960. Min Act: -0.1700
Data Index: 6017297 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.9648. Min Act: -0.1700
Data Index: 3068199 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.9648. Min Act: -0.1700
Data Index: 5485023 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.8710. Min Act: -0.1700
Data Index: 5935027 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.8085. Min Act: -0.1700
Data Index: 7023418 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7773. Min Act: -0.1700
Data Index: 962528 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 8314004 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 5643828 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7148. Min Act: -0.1700
Data Index: 4067281 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7148. Min Act: -0.1700
Data Index: 5506220 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7148. Min Act: -0.1700
Data Index: 1698192 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7148. Min Act: -0.1700
Data Index: 3385902 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6835. Min Act: -0.1700
Data Index: 2237134 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7148. Min Act: -0.1700
Data Index: 501128 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6523. Min Act: -0.1700
Data Index: 2868647 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6523. Min Act: -0.1700
Data Index: 6958000 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6210. Min Act: -0.1700
Data Index: 7830184 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6210. Min Act: -0.1700
Data Index: 915941 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6210. Min Act: -0.1700
Data Index: 5405207 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6210. Min Act: -0.1700
Data Index: 3236363 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19