Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5036 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2075. Min Range: -5.2075
Max Act: 5.2075. Min Act: -0.1700
Data Index: 7734825 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2075. Min Range: -5.2075
Max Act: 5.2075. Min Act: -0.1700
Data Index: 7750553 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2075. Min Range: -5.2075
Max Act: 5.1137. Min Act: -0.1700
Data Index: 3618783 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2075. Min Range: -5.2075
Max Act: 5.0825. Min Act: -0.1700
Data Index: 6187369 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2075. Min Range: -5.2075
Max Act: 5.0825. Min Act: -0.1700
Data Index: 4394656 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2075. Min Range: -5.2075
Max Act: 5.0512. Min Act: -0.1700
Data Index: 2894477 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.9887. Min Act: -0.1700
Data Index: 574683 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.9887. Min Act: -0.1700
Data Index: 2511084 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.9575. Min Act: -0.1700
Data Index: 805728 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.9575. Min Act: -0.1700
Data Index: 4680497 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.9575. Min Act: -0.1700
Data Index: 8555031 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.9575. Min Act: -0.1700
Data Index: 4063296 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.9262. Min Act: -0.1700
Data Index: 6737543 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.9262. Min Act: -0.1700
Data Index: 6860192 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.8950. Min Act: -0.1700
Data Index: 5203197 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.9262. Min Act: -0.1700
Data Index: 2387767 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.8325. Min Act: -0.1700
Data Index: 4782962 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.8325. Min Act: -0.1700
Data Index: 3859325 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.8325. Min Act: -0.1700
Data Index: 2111243 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2075. Min Range: -5.2075
Max Act: 4.8012. Min Act: -0.1700
Data Index: 2942015 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19