Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2235 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.6011. Min Act: -0.1700
Data Index: 4767270 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.5698. Min Act: -0.1700
Data Index: 4572858 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3198. Min Act: -0.1700
Data Index: 179648 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2885. Min Act: -0.1700
Data Index: 2581248 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2885. Min Act: -0.1700
Data Index: 1910084 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2573. Min Act: -0.1700
Data Index: 4767272 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2573. Min Act: -0.1700
Data Index: 6640231 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1948. Min Act: -0.1700
Data Index: 5670905 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1635. Min Act: -0.1700
Data Index: 5733026 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1635. Min Act: -0.1700
Data Index: 703436 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1323. Min Act: -0.1700
Data Index: 3159819 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1323. Min Act: -0.1700
Data Index: 8775355 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1323. Min Act: -0.1700
Data Index: 3618742 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1323. Min Act: -0.1700
Data Index: 7614103 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1010. Min Act: -0.1700
Data Index: 8789259 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1010. Min Act: -0.1700
Data Index: 3360161 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0698. Min Act: -0.1700
Data Index: 7354107 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0698. Min Act: -0.1700
Data Index: 7486939 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0698. Min Act: -0.1700
Data Index: 3326282 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0385. Min Act: -0.1700
Data Index: 7398329 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19