Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1622. Min Range: -8.1622
Max Act: 8.1622. Min Act: -0.1700
Data Index: 1965222 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1622. Min Range: -8.1622
Max Act: 8.1622. Min Act: -0.1700
Data Index: 2772429 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.8185. Min Act: -0.1700
Data Index: 7823488 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.8185. Min Act: -0.1700
Data Index: 3646926 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.7560. Min Act: -0.1700
Data Index: 879472 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.7247. Min Act: -0.1700
Data Index: 5131335 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.5685. Min Act: -0.1700
Data Index: 5116271 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.5685. Min Act: -0.1700
Data Index: 5993814 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.4747. Min Act: -0.1700
Data Index: 6768461 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.4435. Min Act: -0.1700
Data Index: 4015768 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.3810. Min Act: -0.1700
Data Index: 750327 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.3497. Min Act: -0.1700
Data Index: 5820826 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.3185. Min Act: -0.1700
Data Index: 3841381 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.3185. Min Act: -0.1700
Data Index: 2706348 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.3185. Min Act: -0.1700
Data Index: 5547527 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.2872. Min Act: -0.1700
Data Index: 7007755 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.2872. Min Act: -0.1700
Data Index: 6457674 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.2560. Min Act: -0.1700
Data Index: 7557487 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.2560. Min Act: -0.1700
Data Index: 2358080 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1622. Min Range: -8.1622
Max Act: 7.2247. Min Act: -0.1700
Data Index: 89118 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19