Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 824 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.9714. Min Act: -0.1700
Data Index: 3442681 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.8152. Min Act: -0.1700
Data Index: 7426470 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.6902. Min Act: -0.1700
Data Index: 3729691 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.6277. Min Act: -0.1700
Data Index: 4405595 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.6277. Min Act: -0.1700
Data Index: 1470546 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.5964. Min Act: -0.1700
Data Index: 6611216 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.5964. Min Act: -0.1700
Data Index: 4159410 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.5652. Min Act: -0.1700
Data Index: 1886375 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.5339. Min Act: -0.1700
Data Index: 6768213 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.4714. Min Act: -0.1700
Data Index: 6782164 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.4714. Min Act: -0.1700
Data Index: 716350 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.5027. Min Act: -0.1700
Data Index: 4668625 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.4402. Min Act: -0.1700
Data Index: 3025144 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.4089. Min Act: -0.1700
Data Index: 3161452 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.4089. Min Act: -0.1700
Data Index: 8366580 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3777. Min Act: -0.1700
Data Index: 8328709 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 8467027 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 8047083 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 668293 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.2839. Min Act: -0.1700
Data Index: 4315600 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19