Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.6909. Min Act: -0.1700
Data Index: 7434493 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.3159. Min Act: -0.1700
Data Index: 8682955 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.2222. Min Act: -0.1700
Data Index: 3049151 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.2222. Min Act: -0.1700
Data Index: 8328431 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.1909. Min Act: -0.1700
Data Index: 1241673 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.1909. Min Act: -0.1700
Data Index: 3168380 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.1284. Min Act: -0.1700
Data Index: 4829035 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.0972. Min Act: -0.1700
Data Index: 7465025 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.0659. Min Act: -0.1700
Data Index: 4535278 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.0347. Min Act: -0.1700
Data Index: 3298902 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6909. Min Range: -6.6909
Max Act: 6.0034. Min Act: -0.1700
Data Index: 4699960 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6909. Min Range: -6.6909
Max Act: 5.9409. Min Act: -0.1700
Data Index: 4599222 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6909. Min Range: -6.6909
Max Act: 5.9409. Min Act: -0.1700
Data Index: 4781340 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6909. Min Range: -6.6909
Max Act: 5.9409. Min Act: -0.1700
Data Index: 790265 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6909. Min Range: -6.6909
Max Act: 5.9409. Min Act: -0.1700
Data Index: 6685098 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6909. Min Range: -6.6909
Max Act: 5.9097. Min Act: -0.1700
Data Index: 5831717 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6909. Min Range: -6.6909
Max Act: 5.8472. Min Act: -0.1700
Data Index: 8430664 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6909. Min Range: -6.6909
Max Act: 5.8784. Min Act: -0.1700
Data Index: 8377581 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6909. Min Range: -6.6909
Max Act: 5.8472. Min Act: -0.1700
Data Index: 4645460 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6909. Min Range: -6.6909
Max Act: 5.8472. Min Act: -0.1700
Data Index: 5488232 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19