Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4832 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2008. Min Range: -4.2008
Max Act: 4.2008. Min Act: -0.1700
Data Index: 6326993 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2008. Min Range: -4.2008
Max Act: 4.2008. Min Act: -0.1700
Data Index: 5552734 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2008. Min Range: -4.2008
Max Act: 4.0758. Min Act: -0.1700
Data Index: 6476695 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2008. Min Range: -4.2008
Max Act: 4.0446. Min Act: -0.1700
Data Index: 874432 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2008. Min Range: -4.2008
Max Act: 4.0446. Min Act: -0.1700
Data Index: 53734 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2008. Min Range: -4.2008
Max Act: 4.0446. Min Act: -0.1700
Data Index: 6839825 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2008. Min Range: -4.2008
Max Act: 4.0446. Min Act: -0.1700
Data Index: 1679402 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2008. Min Range: -4.2008
Max Act: 4.0133. Min Act: -0.1700
Data Index: 2509531 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.9820. Min Act: -0.1700
Data Index: 8285593 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.9508. Min Act: -0.1700
Data Index: 7648183 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.9820. Min Act: -0.1700
Data Index: 2594649 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.9195. Min Act: -0.1700
Data Index: 4993014 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.8883. Min Act: -0.1700
Data Index: 5976742 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.8883. Min Act: -0.1700
Data Index: 6067662 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.8570. Min Act: -0.1700
Data Index: 2986303 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.8883. Min Act: -0.1700
Data Index: 357171 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.8570. Min Act: -0.1700
Data Index: 5538230 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.8570. Min Act: -0.1700
Data Index: 4194979 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.8257. Min Act: -0.1700
Data Index: 4213513 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2008. Min Range: -4.2008
Max Act: 3.8257. Min Act: -0.1700
Data Index: 2188967 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19