Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2487 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0148. Min Range: -4.0148
Max Act: 4.0148. Min Act: -0.1700
Data Index: 6850620 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.9835. Min Act: -0.1700
Data Index: 574984 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.9210. Min Act: -0.1700
Data Index: 2935708 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.8585. Min Act: -0.1700
Data Index: 3956526 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.8897. Min Act: -0.1700
Data Index: 5991915 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.8897. Min Act: -0.1700
Data Index: 3720593 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.8585. Min Act: -0.1700
Data Index: 3256000 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.8272. Min Act: -0.1700
Data Index: 1124952 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.8272. Min Act: -0.1700
Data Index: 4054247 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.8272. Min Act: -0.1700
Data Index: 3364542 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.8272. Min Act: -0.1700
Data Index: 5433950 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.7959. Min Act: -0.1700
Data Index: 5631516 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.7959. Min Act: -0.1700
Data Index: 697803 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.7959. Min Act: -0.1700
Data Index: 1616602 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.7959. Min Act: -0.1700
Data Index: 7309184 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.7646. Min Act: -0.1700
Data Index: 8719902 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.7959. Min Act: -0.1700
Data Index: 5770932 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.7646. Min Act: -0.1700
Data Index: 100134 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.7334. Min Act: -0.1700
Data Index: 3932257 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0148. Min Range: -4.0148
Max Act: 3.7334. Min Act: -0.1700
Data Index: 1021903 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19