Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.4397. Min Act: -0.1700
Data Index: 4128591 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.3772. Min Act: -0.1700
Data Index: 3359564 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.2522. Min Act: -0.1700
Data Index: 6624796 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.2209. Min Act: -0.1700
Data Index: 3636635 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.1584. Min Act: -0.1700
Data Index: 7430853 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.1272. Min Act: -0.1700
Data Index: 3187626 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.1272. Min Act: -0.1700
Data Index: 955200 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.0959. Min Act: -0.1700
Data Index: 7102755 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.0647. Min Act: -0.1700
Data Index: 3636636 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.0334. Min Act: -0.1700
Data Index: 8006492 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.0022. Min Act: -0.1700
Data Index: 2803626 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.0647. Min Act: -0.1700
Data Index: 5114342 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.0334. Min Act: -0.1700
Data Index: 1950331 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.0022. Min Act: -0.1700
Data Index: 5524212 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.0022. Min Act: -0.1700
Data Index: 1223319 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4397. Min Range: -6.4397
Max Act: 5.9709. Min Act: -0.1700
Data Index: 5273252 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4397. Min Range: -6.4397
Max Act: 5.9709. Min Act: -0.1700
Data Index: 2255194 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4397. Min Range: -6.4397
Max Act: 5.9709. Min Act: -0.1700
Data Index: 3712656 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4397. Min Range: -6.4397
Max Act: 6.0022. Min Act: -0.1700
Data Index: 2088235 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4397. Min Range: -6.4397
Max Act: 5.9397. Min Act: -0.1700
Data Index: 4073333 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19