Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4990 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.3085. Min Act: -0.1700
Data Index: 2057882 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.3085. Min Act: -0.1700
Data Index: 2702259 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.2460. Min Act: -0.1700
Data Index: 1859383 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.2460. Min Act: -0.1700
Data Index: 8215860 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.2460. Min Act: -0.1700
Data Index: 8272888 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1835. Min Act: -0.1700
Data Index: 7158113 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1835. Min Act: -0.1700
Data Index: 510380 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1835. Min Act: -0.1700
Data Index: 3136297 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1522. Min Act: -0.1700
Data Index: 4660454 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1522. Min Act: -0.1700
Data Index: 1794644 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1522. Min Act: -0.1700
Data Index: 1057766 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1210. Min Act: -0.1700
Data Index: 3130064 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1210. Min Act: -0.1700
Data Index: 8274755 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1210. Min Act: -0.1700
Data Index: 6874922 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1210. Min Act: -0.1700
Data Index: 5591137 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1210. Min Act: -0.1700
Data Index: 3773186 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1210. Min Act: -0.1700
Data Index: 7364827 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1210. Min Act: -0.1700
Data Index: 2491497 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.1522. Min Act: -0.1700
Data Index: 5142969 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3085. Min Range: -5.3085
Max Act: 5.0897. Min Act: -0.1700
Data Index: 7364828 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19