Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0778. Min Range: -4.0778
Max Act: 4.0778. Min Act: -0.1700
Data Index: 3367410 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0778. Min Range: -4.0778
Max Act: 4.0465. Min Act: -0.1700
Data Index: 3496488 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0778. Min Range: -4.0778
Max Act: 4.0153. Min Act: -0.1700
Data Index: 6140845 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8902. Min Act: -0.1700
Data Index: 6125558 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 7340336 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8590. Min Act: -0.1700
Data Index: 4568290 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8590. Min Act: -0.1700
Data Index: 1230111 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8277. Min Act: -0.1700
Data Index: 1230113 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7964. Min Act: -0.1700
Data Index: 4479083 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.8590. Min Act: -0.1700
Data Index: 4479077 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7964. Min Act: -0.1700
Data Index: 3373896 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7964. Min Act: -0.1700
Data Index: 3099669 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7964. Min Act: -0.1700
Data Index: 6484681 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7964. Min Act: -0.1700
Data Index: 7340332 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7964. Min Act: -0.1700
Data Index: 7490620 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7651. Min Act: -0.1700
Data Index: 6361505 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7651. Min Act: -0.1700
Data Index: 7340334 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7651. Min Act: -0.1700
Data Index: 3998581 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7651. Min Act: -0.1700
Data Index: 7340331 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0778. Min Range: -4.0778
Max Act: 3.7651. Min Act: -0.1700
Data Index: 1477595 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19