Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4854 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.3183. Min Act: -0.1700
Data Index: 3982993 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.2871. Min Act: -0.1700
Data Index: 6376968 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.2871. Min Act: -0.1700
Data Index: 3983008 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.2246. Min Act: -0.1700
Data Index: 3403309 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.1933. Min Act: -0.1700
Data Index: 4852565 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.1308. Min Act: -0.1700
Data Index: 246878 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.0996. Min Act: -0.1700
Data Index: 4996192 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.0371. Min Act: -0.1700
Data Index: 4034685 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.0058. Min Act: -0.1700
Data Index: 8280787 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3183. Min Range: -5.3183
Max Act: 5.0058. Min Act: -0.1700
Data Index: 7460608 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.9746. Min Act: -0.1700
Data Index: 2117744 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.9433. Min Act: -0.1700
Data Index: 8579904 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.9433. Min Act: -0.1700
Data Index: 7211694 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.9121. Min Act: -0.1700
Data Index: 430713 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.9121. Min Act: -0.1700
Data Index: 3819998 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.8808. Min Act: -0.1700
Data Index: 6069219 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.8808. Min Act: -0.1700
Data Index: 7801378 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.8496. Min Act: -0.1700
Data Index: 3860964 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.8808. Min Act: -0.1700
Data Index: 7890280 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3183. Min Range: -5.3183
Max Act: 4.9121. Min Act: -0.1700
Data Index: 8740067 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19