Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 696 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6293. Min Range: -7.6293
Max Act: 7.6293. Min Act: -0.1700
Data Index: 5372879 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6293. Min Range: -7.6293
Max Act: 7.3793. Min Act: -0.1700
Data Index: 2651304 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6293. Min Range: -7.6293
Max Act: 7.2543. Min Act: -0.1700
Data Index: 8690741 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6293. Min Range: -7.6293
Max Act: 7.0043. Min Act: -0.1700
Data Index: 8217638 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6293. Min Range: -7.6293
Max Act: 7.0043. Min Act: -0.1700
Data Index: 4691098 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.9730. Min Act: -0.1700
Data Index: 3636503 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.9730. Min Act: -0.1700
Data Index: 2339501 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.9105. Min Act: -0.1700
Data Index: 110442 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.9105. Min Act: -0.1700
Data Index: 2339500 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.8793. Min Act: -0.1700
Data Index: 6031814 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.9105. Min Act: -0.1700
Data Index: 1518567 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.9418. Min Act: -0.1700
Data Index: 8578599 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.8793. Min Act: -0.1700
Data Index: 175817 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.8480. Min Act: -0.1700
Data Index: 3227844 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.8793. Min Act: -0.1700
Data Index: 7014605 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.8793. Min Act: -0.1700
Data Index: 7795161 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.8480. Min Act: -0.1700
Data Index: 3119996 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.8480. Min Act: -0.1700
Data Index: 1368488 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.8480. Min Act: -0.1700
Data Index: 7257746 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6293. Min Range: -7.6293
Max Act: 6.8168. Min Act: -0.1700
Data Index: 5259318 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19