Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4873 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1781. Min Range: -4.1781
Max Act: 4.1781. Min Act: -0.1700
Data Index: 906083 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1781. Min Range: -4.1781
Max Act: 4.1781. Min Act: -0.1700
Data Index: 864674 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1781. Min Range: -4.1781
Max Act: 4.1469. Min Act: -0.1700
Data Index: 7402704 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.9593. Min Act: -0.1700
Data Index: 4521979 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.9593. Min Act: -0.1700
Data Index: 6409813 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.9280. Min Act: -0.1700
Data Index: 2486464 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8968. Min Act: -0.1700
Data Index: 1736814 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8968. Min Act: -0.1700
Data Index: 5040168 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8655. Min Act: -0.1700
Data Index: 7194849 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8655. Min Act: -0.1700
Data Index: 3383183 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8655. Min Act: -0.1700
Data Index: 7329408 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8655. Min Act: -0.1700
Data Index: 6102840 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8342. Min Act: -0.1700
Data Index: 7324982 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8030. Min Act: -0.1700
Data Index: 3011240 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8342. Min Act: -0.1700
Data Index: 7011335 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8342. Min Act: -0.1700
Data Index: 6881662 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8342. Min Act: -0.1700
Data Index: 371668 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8030. Min Act: -0.1700
Data Index: 4109589 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8030. Min Act: -0.1700
Data Index: 719086 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1781. Min Range: -4.1781
Max Act: 3.8342. Min Act: -0.1700
Data Index: 4186512 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19