Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 153 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.9303. Min Act: -0.1700
Data Index: 3069331 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.8669. Min Act: -0.1700
Data Index: 8505510 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.8351. Min Act: -0.1700
Data Index: 6024834 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.8351. Min Act: -0.1700
Data Index: 3013017 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.8192. Min Act: -0.1700
Data Index: 5369638 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.8351. Min Act: -0.1700
Data Index: 8371993 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.8351. Min Act: -0.1700
Data Index: 4337671 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.8192. Min Act: -0.1700
Data Index: 8684312 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7714. Min Act: -0.1700
Data Index: 6478503 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7714. Min Act: -0.1700
Data Index: 40165 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7555. Min Act: -0.1700
Data Index: 173861 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7555. Min Act: -0.1700
Data Index: 5842841 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7555. Min Act: -0.1700
Data Index: 3844667 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7714. Min Act: -0.1700
Data Index: 8686850 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7555. Min Act: -0.1700
Data Index: 5141258 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7395. Min Act: -0.1700
Data Index: 8170619 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7555. Min Act: -0.1700
Data Index: 6415456 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7235. Min Act: -0.1700
Data Index: 3069353 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7555. Min Act: -0.1700
Data Index: 2814879 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9303. Min Range: -2.9303
Max Act: 2.7395. Min Act: -0.1700
Data Index: 7412009 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19