Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6213 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.7347. Min Act: -0.1700
Data Index: 3638025 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.7347. Min Act: -0.1700
Data Index: 5973915 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.5784. Min Act: -0.1700
Data Index: 2459270 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.5784. Min Act: -0.1700
Data Index: 8761893 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.4847. Min Act: -0.1700
Data Index: 4286021 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.4847. Min Act: -0.1700
Data Index: 1992244 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.4222. Min Act: -0.1700
Data Index: 7430181 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.4222. Min Act: -0.1700
Data Index: 3010990 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.4222. Min Act: -0.1700
Data Index: 6621439 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.4222. Min Act: -0.1700
Data Index: 8142299 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.4222. Min Act: -0.1700
Data Index: 8388274 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.3909. Min Act: -0.1700
Data Index: 5333804 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.3909. Min Act: -0.1700
Data Index: 192678 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.3909. Min Act: -0.1700
Data Index: 6077246 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.3909. Min Act: -0.1700
Data Index: 6581936 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.3597. Min Act: -0.1700
Data Index: 8532647 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.3597. Min Act: -0.1700
Data Index: 1324007 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.3284. Min Act: -0.1700
Data Index: 7348441 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.2972. Min Act: -0.1700
Data Index: 5991199 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7347. Min Range: -6.7347
Max Act: 6.2972. Min Act: -0.1700
Data Index: 2467242 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19