Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.3969. Min Act: -0.1700
Data Index: 241437 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.2557. Min Act: -0.1700
Data Index: 4673025 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.2557. Min Act: -0.1700
Data Index: 3499733 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.2242. Min Act: -0.1700
Data Index: 2094994 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.2399. Min Act: -0.1700
Data Index: 1090085 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.2399. Min Act: -0.1700
Data Index: 8425717 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.2399. Min Act: -0.1700
Data Index: 7305564 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.2242. Min Act: -0.1700
Data Index: 8457664 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.2085. Min Act: -0.1700
Data Index: 5498481 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.2242. Min Act: -0.1700
Data Index: 2205355 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.1613. Min Act: -0.1700
Data Index: 2627534 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.1613. Min Act: -0.1700
Data Index: 8239675 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.1613. Min Act: -0.1700
Data Index: 6960706 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.1456. Min Act: -0.1700
Data Index: 3922791 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.1613. Min Act: -0.1700
Data Index: 8065854 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.1298. Min Act: -0.1700
Data Index: 2087771 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.0983. Min Act: -0.1700
Data Index: 3164151 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.0983. Min Act: -0.1700
Data Index: 6210720 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.0983. Min Act: -0.1700
Data Index: 3295744 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3969. Min Range: -3.3969
Max Act: 3.0826. Min Act: -0.1700
Data Index: 1415515 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19