Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.4589. Min Act: -0.1700
Data Index: 255298 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.4276. Min Act: -0.1700
Data Index: 4821 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.3651. Min Act: -0.1700
Data Index: 464783 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.2401. Min Act: -0.1700
Data Index: 1422667 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.2089. Min Act: -0.1700
Data Index: 1131945 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.2089. Min Act: -0.1700
Data Index: 6502627 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.2089. Min Act: -0.1700
Data Index: 4339276 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.1464. Min Act: -0.1700
Data Index: 2345157 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.1151. Min Act: -0.1700
Data Index: 6981201 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.0839. Min Act: -0.1700
Data Index: 965542 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4589. Min Range: -6.4589
Max Act: 6.0526. Min Act: -0.1700
Data Index: 6291705 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4589. Min Range: -6.4589
Max Act: 5.9589. Min Act: -0.1700
Data Index: 3298086 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4589. Min Range: -6.4589
Max Act: 5.8964. Min Act: -0.1700
Data Index: 1260478 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4589. Min Range: -6.4589
Max Act: 5.8651. Min Act: -0.1700
Data Index: 1315466 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4589. Min Range: -6.4589
Max Act: 5.8651. Min Act: -0.1700
Data Index: 7163468 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4589. Min Range: -6.4589
Max Act: 5.8339. Min Act: -0.1700
Data Index: 1323100 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4589. Min Range: -6.4589
Max Act: 5.8026. Min Act: -0.1700
Data Index: 4612045 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4589. Min Range: -6.4589
Max Act: 5.8026. Min Act: -0.1700
Data Index: 2818037 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4589. Min Range: -6.4589
Max Act: 5.7714. Min Act: -0.1700
Data Index: 8806575 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4589. Min Range: -6.4589
Max Act: 5.7714. Min Act: -0.1700
Data Index: 6125139 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19