Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5922 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.2797. Min Act: -0.1700
Data Index: 4146369 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.3110. Min Act: -0.1700
Data Index: 7836444 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.2485. Min Act: -0.1700
Data Index: 7552633 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.2485. Min Act: -0.1700
Data Index: 3038857 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.2172. Min Act: -0.1700
Data Index: 6509952 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.1860. Min Act: -0.1700
Data Index: 6361657 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.1547. Min Act: -0.1700
Data Index: 1710021 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.1547. Min Act: -0.1700
Data Index: 3004728 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.1547. Min Act: -0.1700
Data Index: 1014566 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.1235. Min Act: -0.1700
Data Index: 7141999 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.1235. Min Act: -0.1700
Data Index: 7374089 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.0922. Min Act: -0.1700
Data Index: 6509951 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.0922. Min Act: -0.1700
Data Index: 5447764 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.0922. Min Act: -0.1700
Data Index: 3032081 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.0610. Min Act: -0.1700
Data Index: 2982076 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.0610. Min Act: -0.1700
Data Index: 4007036 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.0297. Min Act: -0.1700
Data Index: 4995086 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.0297. Min Act: -0.1700
Data Index: 3806456 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.0297. Min Act: -0.1700
Data Index: 4391573 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3110. Min Range: -5.3110
Max Act: 5.0297. Min Act: -0.1700
Data Index: 5602574 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19