Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.3922. Min Act: -0.1700
Data Index: 4268667 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.3922. Min Act: -0.1700
Data Index: 5677561 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.3297. Min Act: -0.1700
Data Index: 961206 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.3297. Min Act: -0.1700
Data Index: 1428258 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.3297. Min Act: -0.1700
Data Index: 374940 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.2672. Min Act: -0.1700
Data Index: 2634289 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.2047. Min Act: -0.1700
Data Index: 1955976 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1422. Min Act: -0.1698
Data Index: 8423989 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1422. Min Act: -0.1700
Data Index: 1913921 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1422. Min Act: -0.1700
Data Index: 482858 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1422. Min Act: -0.1700
Data Index: 2015842 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1422. Min Act: -0.1700
Data Index: 6277622 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1422. Min Act: -0.1700
Data Index: 788400 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1109. Min Act: -0.1700
Data Index: 6362298 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1109. Min Act: -0.1700
Data Index: 7303197 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.0797. Min Act: -0.1700
Data Index: 1055578 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1109. Min Act: -0.1700
Data Index: 7267800 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1109. Min Act: -0.1700
Data Index: 5598250 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1109. Min Act: -0.1700
Data Index: 6613654 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3922. Min Range: -7.3922
Max Act: 7.1109. Min Act: -0.1700
Data Index: 500356 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19