Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.9446. Min Act: -0.1700
Data Index: 4996393 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.2884. Min Act: -0.1700
Data Index: 5991124 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.2571. Min Act: -0.1700
Data Index: 3810633 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.1946. Min Act: -0.1700
Data Index: 3881717 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.2259. Min Act: -0.1700
Data Index: 6357638 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.1946. Min Act: -0.1700
Data Index: 1231499 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.1946. Min Act: -0.1700
Data Index: 8126746 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.1009. Min Act: -0.1700
Data Index: 3326877 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.1009. Min Act: -0.1700
Data Index: 3250914 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.1009. Min Act: -0.1700
Data Index: 2114068 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.1321. Min Act: -0.1700
Data Index: 2922240 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.0384. Min Act: -0.1700
Data Index: 5534161 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.0071. Min Act: -0.1700
Data Index: 7529964 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9446. Min Range: -5.9446
Max Act: 5.0071. Min Act: -0.1700
Data Index: 1277985 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9446. Min Range: -5.9446
Max Act: 4.9759. Min Act: -0.1700
Data Index: 5596446 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9446. Min Range: -5.9446
Max Act: 4.9759. Min Act: -0.1700
Data Index: 2893106 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9446. Min Range: -5.9446
Max Act: 4.9759. Min Act: -0.1700
Data Index: 588598 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9446. Min Range: -5.9446
Max Act: 4.9759. Min Act: -0.1700
Data Index: 5563625 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9446. Min Range: -5.9446
Max Act: 4.9759. Min Act: -0.1700
Data Index: 1428988 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9446. Min Range: -5.9446
Max Act: 4.9759. Min Act: -0.1700
Data Index: 1571625 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19