Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.3161. Min Act: -0.1700
Data Index: 1247259 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.1286. Min Act: -0.1700
Data Index: 6179767 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.0661. Min Act: -0.1700
Data Index: 5795611 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.0661. Min Act: -0.1700
Data Index: 1631912 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.9411. Min Act: -0.1700
Data Index: 2271394 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.9098. Min Act: -0.1700
Data Index: 3113248 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.8473. Min Act: -0.1700
Data Index: 965193 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7848. Min Act: -0.1700
Data Index: 8385680 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7848. Min Act: -0.1700
Data Index: 4386113 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7223. Min Act: -0.1700
Data Index: 3323476 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7223. Min Act: -0.1700
Data Index: 6216107 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7223. Min Act: -0.1700
Data Index: 8061105 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.6598. Min Act: -0.1700
Data Index: 6775280 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.6286. Min Act: -0.1700
Data Index: 7174074 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.6286. Min Act: -0.1700
Data Index: 8768668 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.5973. Min Act: -0.1700
Data Index: 5747411 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.6286. Min Act: -0.1700
Data Index: 880998 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.5973. Min Act: -0.1700
Data Index: 5311064 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.6286. Min Act: -0.1700
Data Index: 5543376 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.5661. Min Act: -0.1700
Data Index: 1566754 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19