Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 597 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6303. Min Range: -8.6303
Max Act: 8.6303. Min Act: -0.1700
Data Index: 197761 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6303. Min Range: -8.6303
Max Act: 8.3803. Min Act: -0.1700
Data Index: 3034288 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6303. Min Range: -8.6303
Max Act: 8.0678. Min Act: -0.1700
Data Index: 8520887 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6303. Min Range: -8.6303
Max Act: 8.0678. Min Act: -0.1700
Data Index: 5779769 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6303. Min Range: -8.6303
Max Act: 8.0991. Min Act: -0.1700
Data Index: 6749528 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.7553. Min Act: -0.1700
Data Index: 4700684 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.4741. Min Act: -0.1700
Data Index: 2188584 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.4428. Min Act: -0.1700
Data Index: 251421 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.4428. Min Act: -0.1700
Data Index: 1865102 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.4428. Min Act: -0.1700
Data Index: 2040570 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.3803. Min Act: -0.1700
Data Index: 2412936 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.3178. Min Act: -0.1700
Data Index: 197764 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.3491. Min Act: -0.1700
Data Index: 8497305 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.2866. Min Act: -0.1700
Data Index: 1116785 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.2553. Min Act: -0.1700
Data Index: 2188587 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.2866. Min Act: -0.1700
Data Index: 5779764 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.2553. Min Act: -0.1700
Data Index: 1918344 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.2553. Min Act: -0.1700
Data Index: 7110442 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.2553. Min Act: -0.1700
Data Index: 1483191 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6303. Min Range: -8.6303
Max Act: 7.2553. Min Act: -0.1700
Data Index: 8704881 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19