Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.4540. Min Act: -0.1700
Data Index: 6037777 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.2352. Min Act: -0.1700
Data Index: 4173756 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.2352. Min Act: -0.1700
Data Index: 1197470 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.2040. Min Act: -0.1700
Data Index: 4617966 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.1727. Min Act: -0.1700
Data Index: 6226783 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.1727. Min Act: -0.1700
Data Index: 7647142 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.1727. Min Act: -0.1700
Data Index: 8705061 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.1102. Min Act: -0.1700
Data Index: 5071547 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.1102. Min Act: -0.1700
Data Index: 8012270 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.0477. Min Act: -0.1700
Data Index: 2425243 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.0790. Min Act: -0.1700
Data Index: 600467 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.0477. Min Act: -0.1700
Data Index: 7696971 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.0165. Min Act: -0.1700
Data Index: 2360977 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.0165. Min Act: -0.1700
Data Index: 5699422 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.0165. Min Act: -0.1700
Data Index: 290892 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4540. Min Range: -7.4540
Max Act: 6.9852. Min Act: -0.1700
Data Index: 1332814 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.0165. Min Act: -0.1700
Data Index: 803238 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4540. Min Range: -7.4540
Max Act: 7.0165. Min Act: -0.1700
Data Index: 7346798 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4540. Min Range: -7.4540
Max Act: 6.9852. Min Act: -0.1700
Data Index: 4990732 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4540. Min Range: -7.4540
Max Act: 6.9852. Min Act: -0.1700
Data Index: 4176634 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19