Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 463 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.4073. Min Act: -0.1700
Data Index: 7799572 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3760. Min Act: -0.1700
Data Index: 1349923 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3760. Min Act: -0.1700
Data Index: 1522076 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3760. Min Act: -0.1700
Data Index: 6298225 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3760. Min Act: -0.1700
Data Index: 6746164 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3448. Min Act: -0.1700
Data Index: 4231356 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3760. Min Act: -0.1700
Data Index: 3666105 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3448. Min Act: -0.1700
Data Index: 1867343 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3135. Min Act: -0.1700
Data Index: 3091606 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.2823. Min Act: -0.1700
Data Index: 2336441 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3135. Min Act: -0.1700
Data Index: 2051473 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3135. Min Act: -0.1700
Data Index: 6295690 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.2823. Min Act: -0.1700
Data Index: 2147844 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.2823. Min Act: -0.1700
Data Index: 3689755 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.2823. Min Act: -0.1700
Data Index: 8719313 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.2510. Min Act: -0.1700
Data Index: 721107 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3135. Min Act: -0.1700
Data Index: 26613 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.2823. Min Act: -0.1700
Data Index: 4837374 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.2823. Min Act: -0.1700
Data Index: 451474 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4073. Min Range: -4.4073
Max Act: 4.3135. Min Act: -0.1700
Data Index: 7081364 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19