Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 675 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1129. Min Range: -5.1129
Max Act: 5.1129. Min Act: -0.1700
Data Index: 211816 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1129. Min Range: -5.1129
Max Act: 5.0816. Min Act: -0.1700
Data Index: 5366305 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.9254. Min Act: -0.1700
Data Index: 1537672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.9254. Min Act: -0.1700
Data Index: 4138058 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.9254. Min Act: -0.1700
Data Index: 2611768 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.9254. Min Act: -0.1700
Data Index: 2702681 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.9254. Min Act: -0.1700
Data Index: 6335552 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8941. Min Act: -0.1700
Data Index: 2173444 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8941. Min Act: -0.1700
Data Index: 2966155 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8629. Min Act: -0.1700
Data Index: 5028360 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8316. Min Act: -0.1699
Data Index: 3438081 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8316. Min Act: -0.1700
Data Index: 4074570 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8004. Min Act: -0.1700
Data Index: 2081731 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8316. Min Act: -0.1700
Data Index: 87790 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8316. Min Act: -0.1700
Data Index: 1660426 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8316. Min Act: -0.1699
Data Index: 4395228 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8316. Min Act: -0.1700
Data Index: 4507903 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8316. Min Act: -0.1700
Data Index: 1041541 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8316. Min Act: -0.1700
Data Index: 830950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1129. Min Range: -5.1129
Max Act: 4.8316. Min Act: -0.1700
Data Index: 1176622 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19