Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.6374. Min Act: -0.1700
Data Index: 2697811 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.5124. Min Act: -0.1700
Data Index: 4395713 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.2624. Min Act: -0.1700
Data Index: 4926083 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.2624. Min Act: -0.1700
Data Index: 8183803 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.2312. Min Act: -0.1700
Data Index: 5327773 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.1999. Min Act: -0.1700
Data Index: 4395710 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.1687. Min Act: -0.1700
Data Index: 2584950 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.1374. Min Act: -0.1700
Data Index: 2584949 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.1374. Min Act: -0.1700
Data Index: 6151598 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.0749. Min Act: -0.1700
Data Index: 1962636 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.0749. Min Act: -0.1700
Data Index: 5392497 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.0749. Min Act: -0.1700
Data Index: 1080532 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.0437. Min Act: -0.1700
Data Index: 7227562 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6374. Min Range: -6.6374
Max Act: 6.0124. Min Act: -0.1700
Data Index: 6375954 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6374. Min Range: -6.6374
Max Act: 5.9812. Min Act: -0.1700
Data Index: 1962637 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6374. Min Range: -6.6374
Max Act: 5.9812. Min Act: -0.1700
Data Index: 3722702 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6374. Min Range: -6.6374
Max Act: 5.9499. Min Act: -0.1700
Data Index: 7977732 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6374. Min Range: -6.6374
Max Act: 5.9812. Min Act: -0.1700
Data Index: 2931801 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6374. Min Range: -6.6374
Max Act: 5.9499. Min Act: -0.1700
Data Index: 2341457 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6374. Min Range: -6.6374
Max Act: 5.9499. Min Act: -0.1700
Data Index: 8313312 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19