Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.5454. Min Act: -0.1700
Data Index: 8480194 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4969. Min Act: -0.1700
Data Index: 4214894 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4807. Min Act: -0.1700
Data Index: 4447290 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4644. Min Act: -0.1700
Data Index: 8767062 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4644. Min Act: -0.1700
Data Index: 6713293 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4482. Min Act: -0.1700
Data Index: 5575292 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4482. Min Act: -0.1700
Data Index: 6731826 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4482. Min Act: -0.1700
Data Index: 6568483 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4319. Min Act: -0.1700
Data Index: 7479004 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4319. Min Act: -0.1700
Data Index: 2862607 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4319. Min Act: -0.1700
Data Index: 154484 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4319. Min Act: -0.1700
Data Index: 8138790 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4319. Min Act: -0.1700
Data Index: 266006 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4156. Min Act: -0.1700
Data Index: 2577239 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4156. Min Act: -0.1700
Data Index: 6706639 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4156. Min Act: -0.1700
Data Index: 1165687 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4156. Min Act: -0.1700
Data Index: 1165709 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4156. Min Act: -0.1700
Data Index: 7708281 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4156. Min Act: -0.1700
Data Index: 5432451 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5454. Min Range: -2.5454
Max Act: 2.4156. Min Act: -0.1700
Data Index: 399373 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19