Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1672 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.8864. Min Act: -0.1700
Data Index: 4789137 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.7301. Min Act: -0.1700
Data Index: 515480 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.6051. Min Act: -0.1700
Data Index: 6380619 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.5426. Min Act: -0.1700
Data Index: 892936 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.5426. Min Act: -0.1700
Data Index: 724064 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.4801. Min Act: -0.1700
Data Index: 1478051 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.4801. Min Act: -0.1700
Data Index: 5802468 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.4801. Min Act: -0.1700
Data Index: 8327895 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.4489. Min Act: -0.1700
Data Index: 3115090 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.4489. Min Act: -0.1700
Data Index: 7376613 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.4489. Min Act: -0.1700
Data Index: 4555064 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.4801. Min Act: -0.1700
Data Index: 6726770 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.4176. Min Act: -0.1700
Data Index: 7901333 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.3864. Min Act: -0.1700
Data Index: 7801018 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.3551. Min Act: -0.1700
Data Index: 7571970 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.3551. Min Act: -0.1700
Data Index: 3543100 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.3551. Min Act: -0.1700
Data Index: 7347104 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.3551. Min Act: -0.1700
Data Index: 5098354 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.3239. Min Act: -0.1700
Data Index: 628291 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8864. Min Range: -6.8864
Max Act: 6.2926. Min Act: -0.1700
Data Index: 1835276 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19