Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 990 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.4484. Min Act: -0.1700
Data Index: 8383963 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.2609. Min Act: -0.1700
Data Index: 497049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1984. Min Act: -0.1700
Data Index: 8059769 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1984. Min Act: -0.1700
Data Index: 2488436 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1984. Min Act: -0.1700
Data Index: 4480190 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1984. Min Act: -0.1699
Data Index: 5632053 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1984. Min Act: -0.1699
Data Index: 8182884 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1671. Min Act: -0.1700
Data Index: 2231238 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1671. Min Act: -0.1696
Data Index: 1024498 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1359. Min Act: -0.1700
Data Index: 3340415 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1359. Min Act: -0.1699
Data Index: 2658443 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1359. Min Act: -0.1700
Data Index: 1704401 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1359. Min Act: -0.1700
Data Index: 8739107 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1359. Min Act: -0.1700
Data Index: 7068507 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1359. Min Act: -0.1700
Data Index: 8567610 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1359. Min Act: -0.1700
Data Index: 4272780 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1671. Min Act: -0.1700
Data Index: 3960461 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1359. Min Act: -0.1700
Data Index: 8006580 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1046. Min Act: -0.1699
Data Index: 1468290 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4484. Min Range: -5.4484
Max Act: 5.1046. Min Act: -0.1700
Data Index: 6040370 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19