Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6341 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.7536. Min Act: -0.1700
Data Index: 3125070 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.5036. Min Act: -0.1700
Data Index: 3269133 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.3786. Min Act: -0.1700
Data Index: 3193561 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.3473. Min Act: -0.1700
Data Index: 3422230 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2848. Min Act: -0.1700
Data Index: 8755866 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2848. Min Act: -0.1700
Data Index: 3474231 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2223. Min Act: -0.1700
Data Index: 747322 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2223. Min Act: -0.1700
Data Index: 3986873 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2223. Min Act: -0.1700
Data Index: 5767683 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.2223. Min Act: -0.1700
Data Index: 4552915 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.1286. Min Act: -0.1700
Data Index: 2133286 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.1286. Min Act: -0.1700
Data Index: 647876 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.0973. Min Act: -0.1700
Data Index: 1230523 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.0973. Min Act: -0.1700
Data Index: 2566876 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.0661. Min Act: -0.1700
Data Index: 7020740 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.0348. Min Act: -0.1700
Data Index: 490471 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.0348. Min Act: -0.1700
Data Index: 7037143 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.0348. Min Act: -0.1700
Data Index: 1285187 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.0036. Min Act: -0.1700
Data Index: 5736202 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7536. Min Range: -7.7536
Max Act: 7.0348. Min Act: -0.1700
Data Index: 3077057 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19