Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3965 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.4545. Min Act: -0.1700
Data Index: 5070420 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3918. Min Act: -0.1700
Data Index: 4705482 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3918. Min Act: -0.1700
Data Index: 1650905 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3605. Min Act: -0.1700
Data Index: 2162958 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 7366163 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 8822489 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2977. Min Act: -0.1700
Data Index: 4060982 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 4239729 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 3997631 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 5823154 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 3320669 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 577882 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 1766198 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 5119604 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 3675791 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2977. Min Act: -0.1700
Data Index: 3007842 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2977. Min Act: -0.1700
Data Index: 3329222 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2977. Min Act: -0.1700
Data Index: 997994 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2977. Min Act: -0.1700
Data Index: 3329227 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2977. Min Act: -0.1700
Data Index: 4761433 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19