Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2197 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.7138. Min Act: -0.1700
Data Index: 789330 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.8076. Min Act: -0.1700
Data Index: 4667274 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.7138. Min Act: -0.1700
Data Index: 4415138 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.6826. Min Act: -0.1700
Data Index: 2096025 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.6513. Min Act: -0.1700
Data Index: 229063 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.7138. Min Act: -0.1700
Data Index: 8300748 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.6513. Min Act: -0.1700
Data Index: 8721368 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.6201. Min Act: -0.1700
Data Index: 4783265 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.5576. Min Act: -0.1700
Data Index: 723895 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.6201. Min Act: -0.1700
Data Index: 5307965 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.5888. Min Act: -0.1700
Data Index: 3601416 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.5888. Min Act: -0.1700
Data Index: 426800 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.5576. Min Act: -0.1700
Data Index: 7568372 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.4951. Min Act: -0.1700
Data Index: 6697183 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.3701. Min Act: -0.1700
Data Index: 3492236 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.4326. Min Act: -0.1700
Data Index: 5548238 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.5263. Min Act: -0.1700
Data Index: 4993152 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.4638. Min Act: -0.1700
Data Index: 4537012 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.4638. Min Act: -0.1700
Data Index: 521507 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8076. Min Range: -5.8076
Max Act: 5.4326. Min Act: -0.1700
Data Index: 1835006 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19