Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1952 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7365. Min Range: -7.7365
Max Act: 7.7365. Min Act: -0.1700
Data Index: 6907008 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7365. Min Range: -7.7365
Max Act: 7.3303. Min Act: -0.1700
Data Index: 8134429 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7365. Min Range: -7.7365
Max Act: 7.1428. Min Act: -0.1700
Data Index: 2201883 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7365. Min Range: -7.7365
Max Act: 7.0178. Min Act: -0.1700
Data Index: 5723734 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.9865. Min Act: -0.1700
Data Index: 5064467 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.9865. Min Act: -0.1700
Data Index: 4703534 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.9553. Min Act: -0.1700
Data Index: 6219892 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.8928. Min Act: -0.1700
Data Index: 3640985 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.8615. Min Act: -0.1700
Data Index: 6372856 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.8615. Min Act: -0.1700
Data Index: 1651476 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.8615. Min Act: -0.1700
Data Index: 4721044 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.8303. Min Act: -0.1700
Data Index: 4144057 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.7365. Min Act: -0.1700
Data Index: 2577343 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.7365. Min Act: -0.1700
Data Index: 5634886 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.7365. Min Act: -0.1700
Data Index: 1318070 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.7365. Min Act: -0.1700
Data Index: 7999822 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.7053. Min Act: -0.1700
Data Index: 5338767 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.6740. Min Act: -0.1700
Data Index: 318777 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.6740. Min Act: -0.1700
Data Index: 6792539 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7365. Min Range: -7.7365
Max Act: 6.6740. Min Act: -0.1700
Data Index: 6907725 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19