Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1727 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.4842. Min Act: -0.1700
Data Index: 1201365 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.4842. Min Act: -0.1700
Data Index: 348766 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.4354. Min Act: -0.1700
Data Index: 2966285 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.4680. Min Act: -0.1700
Data Index: 5168577 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.4354. Min Act: -0.1697
Data Index: 348767 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.4354. Min Act: -0.1700
Data Index: 6634345 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3865. Min Act: -0.1700
Data Index: 3451166 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.4028. Min Act: -0.1700
Data Index: 3903067 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.4028. Min Act: -0.1700
Data Index: 4835101 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3702. Min Act: -0.1700
Data Index: 2298654 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3538. Min Act: -0.1700
Data Index: 5608477 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3538. Min Act: -0.1700
Data Index: 516846 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3374. Min Act: -0.1700
Data Index: 3451165 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3210. Min Act: -0.1700
Data Index: 2279373 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3210. Min Act: -0.1700
Data Index: 4582415 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3210. Min Act: -0.1700
Data Index: 348768 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3046. Min Act: -0.1700
Data Index: 7336277 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.3046. Min Act: -0.1700
Data Index: 3283420 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.2881. Min Act: -0.1700
Data Index: 7105631 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4842. Min Range: -2.4842
Max Act: 2.2881. Min Act: -0.1700
Data Index: 714533 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19