Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.2129. Min Act: -0.1700
Data Index: 5490845 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.1971. Min Act: -0.1700
Data Index: 556033 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.2129. Min Act: -0.1700
Data Index: 4975540 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0869. Min Act: -0.1700
Data Index: 8198016 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0869. Min Act: -0.1700
Data Index: 580423 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0554. Min Act: -0.1700
Data Index: 3472354 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0554. Min Act: -0.1700
Data Index: 8280147 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0554. Min Act: -0.1700
Data Index: 5208656 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0554. Min Act: -0.1700
Data Index: 492338 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0238. Min Act: -0.1700
Data Index: 6213053 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0238. Min Act: -0.1700
Data Index: 650761 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0238. Min Act: -0.1700
Data Index: 2953248 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2129. Min Range: -3.2129
Max Act: 2.9922. Min Act: -0.1700
Data Index: 2988476 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0080. Min Act: -0.1700
Data Index: 2224906 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0080. Min Act: -0.1700
Data Index: 421841 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0080. Min Act: -0.1700
Data Index: 743964 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2129. Min Range: -3.2129
Max Act: 2.9922. Min Act: -0.1700
Data Index: 1902352 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2129. Min Range: -3.2129
Max Act: 2.9922. Min Act: -0.1700
Data Index: 7217427 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2129. Min Range: -3.2129
Max Act: 2.9922. Min Act: -0.1700
Data Index: 3997964 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2129. Min Range: -3.2129
Max Act: 3.0238. Min Act: -0.1700
Data Index: 3063310 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19