Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4979 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5275. Min Range: -4.5275
Max Act: 4.5275. Min Act: -0.1700
Data Index: 3986607 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5275. Min Range: -4.5275
Max Act: 4.0900. Min Act: -0.1700
Data Index: 3535078 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5275. Min Range: -4.5275
Max Act: 4.0275. Min Act: -0.1700
Data Index: 3535071 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.9650. Min Act: -0.1700
Data Index: 8230102 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.9337. Min Act: -0.1700
Data Index: 1668013 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.9337. Min Act: -0.1700
Data Index: 5556489 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.8086. Min Act: -0.1700
Data Index: 7173720 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.8086. Min Act: -0.1700
Data Index: 8623021 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7617. Min Act: -0.1700
Data Index: 756128 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7773. Min Act: -0.1700
Data Index: 102925 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7773. Min Act: -0.1700
Data Index: 1092326 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7617. Min Act: -0.1700
Data Index: 6186278 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7617. Min Act: -0.1700
Data Index: 8360923 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7461. Min Act: -0.1700
Data Index: 6180335 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7617. Min Act: -0.1700
Data Index: 6517462 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7617. Min Act: -0.1700
Data Index: 6313222 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7461. Min Act: -0.1700
Data Index: 6345664 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7617. Min Act: -0.1700
Data Index: 7395926 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7461. Min Act: -0.1700
Data Index: 263523 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5275. Min Range: -4.5275
Max Act: 3.7304. Min Act: -0.1700
Data Index: 7332670 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19