Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.6426. Min Act: -0.1700
Data Index: 1879409 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.6113. Min Act: -0.1700
Data Index: 7855317 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.6270. Min Act: -0.1700
Data Index: 5168714 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.6270. Min Act: -0.1700
Data Index: 1147862 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.6270. Min Act: -0.1700
Data Index: 179444 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5800. Min Act: -0.1700
Data Index: 7694729 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5800. Min Act: -0.1700
Data Index: 8506855 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5800. Min Act: -0.1700
Data Index: 2295413 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5800. Min Act: -0.1700
Data Index: 650854 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5800. Min Act: -0.1700
Data Index: 4344042 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5800. Min Act: -0.1700
Data Index: 8631366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5800. Min Act: -0.1700
Data Index: 8304055 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5800. Min Act: -0.1700
Data Index: 7942224 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5800. Min Act: -0.1700
Data Index: 224260 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5644. Min Act: -0.1700
Data Index: 1619511 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5331. Min Act: -0.1700
Data Index: 4669778 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5174. Min Act: -0.1700
Data Index: 3557481 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5174. Min Act: -0.1700
Data Index: 6827950 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5174. Min Act: -0.1700
Data Index: 5519846 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6426. Min Range: -3.6426
Max Act: 3.5174. Min Act: -0.1700
Data Index: 661153 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19