Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4589 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.5813. Min Act: -0.1700
Data Index: 6898139 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.4057. Min Act: -0.1700
Data Index: 5499044 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.3881. Min Act: -0.1700
Data Index: 1050611 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.3881. Min Act: -0.1700
Data Index: 8543825 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.3352. Min Act: -0.1700
Data Index: 1736335 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2999. Min Act: -0.1700
Data Index: 8065832 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.3176. Min Act: -0.1700
Data Index: 2404110 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.3176. Min Act: -0.1700
Data Index: 4015244 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.3176. Min Act: -0.1700
Data Index: 6929195 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.3176. Min Act: -0.1700
Data Index: 6642945 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.3176. Min Act: -0.1700
Data Index: 6312153 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2999. Min Act: -0.1700
Data Index: 4165495 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2999. Min Act: -0.1700
Data Index: 2969149 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2999. Min Act: -0.1700
Data Index: 3290555 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2999. Min Act: -0.1700
Data Index: 5375174 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2999. Min Act: -0.1700
Data Index: 281594 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2647. Min Act: -0.1700
Data Index: 989730 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2823. Min Act: -0.1700
Data Index: 4589149 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2823. Min Act: -0.1700
Data Index: 4687660 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5813. Min Range: -1.5813
Max Act: 1.2823. Min Act: -0.1700
Data Index: 501981 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19