Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3136 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.3461. Min Act: -0.1700
Data Index: 4867519 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.3148. Min Act: -0.1700
Data Index: 4867517 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.3461. Min Act: -0.1700
Data Index: 4867520 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.1898. Min Act: -0.1700
Data Index: 3777533 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.1898. Min Act: -0.1700
Data Index: 3036122 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.1586. Min Act: -0.1700
Data Index: 4867512 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.1586. Min Act: -0.1700
Data Index: 939455 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.1273. Min Act: -0.1700
Data Index: 4807323 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.0961. Min Act: -0.1700
Data Index: 8428119 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.0648. Min Act: -0.1700
Data Index: 3391912 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.0648. Min Act: -0.1700
Data Index: 6685723 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.0023. Min Act: -0.1700
Data Index: 925918 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.0023. Min Act: -0.1700
Data Index: 7266924 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3461. Min Range: -5.3461
Max Act: 5.0023. Min Act: -0.1700
Data Index: 1673807 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3461. Min Range: -5.3461
Max Act: 4.9711. Min Act: -0.1700
Data Index: 6318063 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3461. Min Range: -5.3461
Max Act: 4.9398. Min Act: -0.1700
Data Index: 3540604 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3461. Min Range: -5.3461
Max Act: 4.9711. Min Act: -0.1700
Data Index: 8341336 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3461. Min Range: -5.3461
Max Act: 4.9398. Min Act: -0.1700
Data Index: 66592 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3461. Min Range: -5.3461
Max Act: 4.9086. Min Act: -0.1700
Data Index: 7819391 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3461. Min Range: -5.3461
Max Act: 4.9086. Min Act: -0.1700
Data Index: 3166278 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19