Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4084 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.4221. Min Act: -0.1700
Data Index: 7061772 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.4534. Min Act: -0.1700
Data Index: 5755453 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.4534. Min Act: -0.1700
Data Index: 465367 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.1721. Min Act: -0.1700
Data Index: 1788387 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.1721. Min Act: -0.1700
Data Index: 2408978 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.1721. Min Act: -0.1700
Data Index: 1226853 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.1409. Min Act: -0.1700
Data Index: 2635884 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.1409. Min Act: -0.1700
Data Index: 613994 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.1096. Min Act: -0.1700
Data Index: 7499224 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.1096. Min Act: -0.1700
Data Index: 4304919 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.0784. Min Act: -0.1700
Data Index: 2044966 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.0784. Min Act: -0.1700
Data Index: 2775412 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.0784. Min Act: -0.1700
Data Index: 2044967 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.0471. Min Act: -0.1700
Data Index: 5590116 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.0471. Min Act: -0.1700
Data Index: 7722830 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.0159. Min Act: -0.1700
Data Index: 1162201 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4534. Min Range: -7.4534
Max Act: 6.9846. Min Act: -0.1700
Data Index: 2507558 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4534. Min Range: -7.4534
Max Act: 7.0159. Min Act: -0.1700
Data Index: 4512021 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4534. Min Range: -7.4534
Max Act: 6.9534. Min Act: -0.1700
Data Index: 7519603 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4534. Min Range: -7.4534
Max Act: 6.9846. Min Act: -0.1700
Data Index: 465365 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19