Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2572. Min Range: -4.2572
Max Act: 4.2572. Min Act: -0.1700
Data Index: 1290077 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2572. Min Range: -4.2572
Max Act: 4.1322. Min Act: -0.1700
Data Index: 5241035 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2572. Min Range: -4.2572
Max Act: 4.0696. Min Act: -0.1700
Data Index: 2704587 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2572. Min Range: -4.2572
Max Act: 4.0384. Min Act: -0.1700
Data Index: 4034875 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2572. Min Range: -4.2572
Max Act: 4.1009. Min Act: -0.1700
Data Index: 4041550 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2572. Min Range: -4.2572
Max Act: 4.0384. Min Act: -0.1700
Data Index: 2500828 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9759. Min Act: -0.1700
Data Index: 1904450 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9759. Min Act: -0.1700
Data Index: 4587307 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9759. Min Act: -0.1700
Data Index: 3286009 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9446. Min Act: -0.1700
Data Index: 1391376 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9133. Min Act: -0.1700
Data Index: 6556984 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9446. Min Act: -0.1700
Data Index: 3766846 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9133. Min Act: -0.1700
Data Index: 3050266 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9446. Min Act: -0.1700
Data Index: 7571129 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9133. Min Act: -0.1700
Data Index: 8635666 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9133. Min Act: -0.1700
Data Index: 4845736 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9133. Min Act: -0.1700
Data Index: 6663701 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9446. Min Act: -0.1700
Data Index: 1025954 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.9133. Min Act: -0.1700
Data Index: 1406576 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2572. Min Range: -4.2572
Max Act: 3.8508. Min Act: -0.1700
Data Index: 939666 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19