Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 909 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.4979. Min Act: -0.1700
Data Index: 5320243 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.4041. Min Act: -0.1700
Data Index: 8177205 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.3103. Min Act: -0.1700
Data Index: 4097245 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.2791. Min Act: -0.1700
Data Index: 8211592 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.2478. Min Act: -0.1700
Data Index: 4317703 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.2478. Min Act: -0.1700
Data Index: 5743721 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.1853. Min Act: -0.1700
Data Index: 6489499 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.1541. Min Act: -0.1700
Data Index: 4872480 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.1541. Min Act: -0.1700
Data Index: 5414411 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.1228. Min Act: -0.1700
Data Index: 8492679 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.1228. Min Act: -0.1700
Data Index: 6399199 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.0916. Min Act: -0.1700
Data Index: 7518145 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.0916. Min Act: -0.1700
Data Index: 6575216 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.0916. Min Act: -0.1700
Data Index: 8656235 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.0916. Min Act: -0.1700
Data Index: 3815240 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.0916. Min Act: -0.1700
Data Index: 5716779 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.0916. Min Act: -0.1700
Data Index: 7320557 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.0603. Min Act: -0.1700
Data Index: 33551 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.0291. Min Act: -0.1700
Data Index: 7088651 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4979. Min Range: -4.4979
Max Act: 4.0291. Min Act: -0.1700
Data Index: 5899523 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19