Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1197 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.5852. Min Act: -0.1700
Data Index: 4155004 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.5852. Min Act: -0.1700
Data Index: 970785 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.4602. Min Act: -0.1700
Data Index: 4297428 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.5227. Min Act: -0.1700
Data Index: 8131657 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.5227. Min Act: -0.1700
Data Index: 8755500 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.5227. Min Act: -0.1700
Data Index: 1920331 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.4602. Min Act: -0.1700
Data Index: 5498023 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.5227. Min Act: -0.1700
Data Index: 2138960 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.5227. Min Act: -0.1700
Data Index: 6171055 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.4602. Min Act: -0.1700
Data Index: 2178421 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.4602. Min Act: -0.1700
Data Index: 4803796 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.4289. Min Act: -0.1700
Data Index: 4202526 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.3977. Min Act: -0.1700
Data Index: 3995637 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.3977. Min Act: -0.1700
Data Index: 5191852 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.3977. Min Act: -0.1700
Data Index: 947626 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.3664. Min Act: -0.1700
Data Index: 8726887 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.3664. Min Act: -0.1700
Data Index: 1353651 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.3664. Min Act: -0.1700
Data Index: 4202591 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.3664. Min Act: -0.1700
Data Index: 521372 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5852. Min Range: -8.5852
Max Act: 8.3352. Min Act: -0.1700
Data Index: 2553690 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19