Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1655 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.4700. Min Act: -0.1700
Data Index: 548011 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.3132. Min Act: -0.1700
Data Index: 6317841 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.3132. Min Act: -0.1700
Data Index: 548012 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.2975. Min Act: -0.1700
Data Index: 6909613 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.2818. Min Act: -0.1700
Data Index: 5179450 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.2504. Min Act: -0.1700
Data Index: 5994639 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1560. Min Act: -0.1700
Data Index: 1754211 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1088. Min Act: -0.1700
Data Index: 548013 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1403. Min Act: -0.1700
Data Index: 681664 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1245. Min Act: -0.1700
Data Index: 1978167 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1088. Min Act: -0.1700
Data Index: 5994638 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.0930. Min Act: -0.1700
Data Index: 4261215 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1088. Min Act: -0.1700
Data Index: 4560178 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1245. Min Act: -0.1700
Data Index: 7031436 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1088. Min Act: -0.1700
Data Index: 5760925 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1088. Min Act: -0.1700
Data Index: 2436447 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.0615. Min Act: -0.1700
Data Index: 3349135 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.0930. Min Act: -0.1700
Data Index: 8340688 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.1088. Min Act: -0.1700
Data Index: 706995 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4700. Min Range: -3.4700
Max Act: 3.0615. Min Act: -0.1700
Data Index: 7071263 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19