Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.5714. Min Act: -0.1700
Data Index: 2792819 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.5088. Min Act: -0.1700
Data Index: 6652392 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.5244. Min Act: -0.1700
Data Index: 3709170 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.5088. Min Act: -0.1700
Data Index: 1386922 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4774. Min Act: -0.1700
Data Index: 3447534 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4618. Min Act: -0.1700
Data Index: 4445038 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4618. Min Act: -0.1700
Data Index: 5728232 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4461. Min Act: -0.1700
Data Index: 5792475 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4148. Min Act: -0.1700
Data Index: 5983546 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4618. Min Act: -0.1700
Data Index: 4586197 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4304. Min Act: -0.1700
Data Index: 1151469 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4148. Min Act: -0.1700
Data Index: 3254354 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4461. Min Act: -0.1700
Data Index: 3398164 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.3991. Min Act: -0.1700
Data Index: 619488 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4148. Min Act: -0.1700
Data Index: 2287981 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4148. Min Act: -0.1700
Data Index: 3054957 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4148. Min Act: -0.1700
Data Index: 1617320 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4304. Min Act: -0.1700
Data Index: 2268815 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4148. Min Act: -0.1700
Data Index: 1145237 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5714. Min Range: -3.5714
Max Act: 3.4148. Min Act: -0.1700
Data Index: 368946 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19