Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1897 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.4817. Min Act: -0.1700
Data Index: 3079861 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.2005. Min Act: -0.1700
Data Index: 1487120 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.0755. Min Act: -0.1700
Data Index: 2619253 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.1380. Min Act: -0.1700
Data Index: 7328630 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4817. Min Range: -6.4817
Max Act: 6.0442. Min Act: -0.1700
Data Index: 2584135 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.9505. Min Act: -0.1700
Data Index: 5208967 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.9505. Min Act: -0.1700
Data Index: 4519455 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.9192. Min Act: -0.1700
Data Index: 6734665 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.9192. Min Act: -0.1700
Data Index: 7084564 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.8880. Min Act: -0.1700
Data Index: 7795900 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.8880. Min Act: -0.1700
Data Index: 4931590 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.8567. Min Act: -0.1700
Data Index: 7563569 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.8255. Min Act: -0.1700
Data Index: 13327 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.8567. Min Act: -0.1700
Data Index: 1902020 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.7942. Min Act: -0.1700
Data Index: 4101514 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.8255. Min Act: -0.1700
Data Index: 3733678 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.8255. Min Act: -0.1700
Data Index: 5106339 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.7630. Min Act: -0.1700
Data Index: 2685358 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.7630. Min Act: -0.1700
Data Index: 4630517 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4817. Min Range: -6.4817
Max Act: 5.7942. Min Act: -0.1700
Data Index: 5653928 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19