Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 923 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.2277. Min Act: -0.1700
Data Index: 6066236 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1964. Min Act: -0.1700
Data Index: 5888171 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1652. Min Act: -0.1700
Data Index: 259120 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 2704023 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1652. Min Act: -0.1700
Data Index: 3423731 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1027. Min Act: -0.1700
Data Index: 6094731 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 7478855 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1652. Min Act: -0.1700
Data Index: 7964872 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 3950919 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 8121335 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 8272016 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1027. Min Act: -0.1700
Data Index: 1840125 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 3316120 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 1456386 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0402. Min Act: -0.1700
Data Index: 3282577 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1339. Min Act: -0.1700
Data Index: 922478 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1027. Min Act: -0.1700
Data Index: 916247 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1027. Min Act: -0.1700
Data Index: 2842130 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.1027. Min Act: -0.1700
Data Index: 4536663 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0714. Min Act: -0.1700
Data Index: 4470218 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19