Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5083 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2566. Min Range: -7.2566
Max Act: 7.2566. Min Act: -0.1700
Data Index: 2601073 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2566. Min Range: -7.2566
Max Act: 7.1316. Min Act: -0.1700
Data Index: 2919194 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2566. Min Range: -7.2566
Max Act: 7.0066. Min Act: -0.1700
Data Index: 1394028 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2566. Min Range: -7.2566
Max Act: 7.0066. Min Act: -0.1700
Data Index: 1621153 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.9128. Min Act: -0.1700
Data Index: 7481119 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.9128. Min Act: -0.1700
Data Index: 3044969 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.9128. Min Act: -0.1700
Data Index: 6590425 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.8816. Min Act: -0.1700
Data Index: 4702432 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.8503. Min Act: -0.1700
Data Index: 2460973 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.8191. Min Act: -0.1700
Data Index: 2533235 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.8191. Min Act: -0.1700
Data Index: 2286536 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.8191. Min Act: -0.1700
Data Index: 2994311 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.7253. Min Act: -0.1700
Data Index: 2880420 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.7253. Min Act: -0.1700
Data Index: 3586137 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.7253. Min Act: -0.1700
Data Index: 7542263 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.7566. Min Act: -0.1700
Data Index: 8055041 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.7253. Min Act: -0.1700
Data Index: 3589400 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.7253. Min Act: -0.1700
Data Index: 8300464 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.6941. Min Act: -0.1700
Data Index: 1123384 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2566. Min Range: -7.2566
Max Act: 6.6941. Min Act: -0.1700
Data Index: 6276949 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19