Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4920 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.9128. Min Act: -0.1700
Data Index: 3827443 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.8972. Min Act: -0.1700
Data Index: 2688229 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.8659. Min Act: -0.1700
Data Index: 8713792 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.8190. Min Act: -0.1700
Data Index: 2127976 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.8034. Min Act: -0.1700
Data Index: 5552981 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.7408. Min Act: -0.1700
Data Index: 3747587 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.7252. Min Act: -0.1700
Data Index: 4399521 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6939. Min Act: -0.1700
Data Index: 5639679 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6939. Min Act: -0.1700
Data Index: 5552963 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6783. Min Act: -0.1700
Data Index: 5095186 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6939. Min Act: -0.1700
Data Index: 5552979 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6939. Min Act: -0.1700
Data Index: 1087754 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6939. Min Act: -0.1700
Data Index: 5639681 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6783. Min Act: -0.1700
Data Index: 5552976 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6783. Min Act: -0.1700
Data Index: 440109 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6783. Min Act: -0.1700
Data Index: 5552955 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6626. Min Act: -0.1700
Data Index: 2648275 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6470. Min Act: -0.1700
Data Index: 5552980 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6626. Min Act: -0.1700
Data Index: 3647245 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9128. Min Range: -3.9128
Max Act: 3.6470. Min Act: -0.1700
Data Index: 3897991 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19