Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.8546. Min Act: -0.1700
Data Index: 120074 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.8233. Min Act: -0.1700
Data Index: 1149373 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.7921. Min Act: -0.1700
Data Index: 4730873 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.7921. Min Act: -0.1700
Data Index: 370624 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.7296. Min Act: -0.1700
Data Index: 2781602 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6983. Min Act: -0.1700
Data Index: 3098654 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6671. Min Act: -0.1700
Data Index: 2508579 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6671. Min Act: -0.1700
Data Index: 2102556 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6983. Min Act: -0.1700
Data Index: 1521697 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6671. Min Act: -0.1700
Data Index: 999235 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6671. Min Act: -0.1699
Data Index: 1687798 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6358. Min Act: -0.1700
Data Index: 2263811 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6046. Min Act: -0.1700
Data Index: 6534190 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6358. Min Act: -0.1700
Data Index: 6070476 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6046. Min Act: -0.1700
Data Index: 2590811 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6358. Min Act: -0.1700
Data Index: 5355228 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6358. Min Act: -0.1700
Data Index: 4515683 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6358. Min Act: -0.1700
Data Index: 3734511 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6046. Min Act: -0.1700
Data Index: 2102560 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8546. Min Range: -5.8546
Max Act: 5.6046. Min Act: -0.1700
Data Index: 5128721 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19