Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1877 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.3698. Min Act: -0.1700
Data Index: 1403920 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.2757. Min Act: -0.1700
Data Index: 774098 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.2599. Min Act: -0.1700
Data Index: 4796813 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.2599. Min Act: -0.1700
Data Index: 5571092 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1026. Min Act: -0.1700
Data Index: 5503147 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1813. Min Act: -0.1700
Data Index: 3110301 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1656. Min Act: -0.1700
Data Index: 5862426 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1656. Min Act: -0.1700
Data Index: 6990689 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1813. Min Act: -0.1700
Data Index: 1939640 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1499. Min Act: -0.1700
Data Index: 7420138 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1184. Min Act: -0.1700
Data Index: 2712564 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1813. Min Act: -0.1700
Data Index: 8811431 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1341. Min Act: -0.1700
Data Index: 8649993 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1499. Min Act: -0.1700
Data Index: 8598056 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1656. Min Act: -0.1700
Data Index: 6156255 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1499. Min Act: -0.1700
Data Index: 4796811 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1184. Min Act: -0.1700
Data Index: 7039131 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1499. Min Act: -0.1700
Data Index: 6953688 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1341. Min Act: -0.1700
Data Index: 1101550 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3698. Min Range: -3.3698
Max Act: 3.1184. Min Act: -0.1700
Data Index: 5314414 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19