Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 107 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.2333. Min Act: -0.1700
Data Index: 7664191 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.2020. Min Act: -0.1700
Data Index: 2029042 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.2020. Min Act: -0.1700
Data Index: 3227334 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.1708. Min Act: -0.1700
Data Index: 6087506 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.1395. Min Act: -0.1700
Data Index: 159480 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.1395. Min Act: -0.1700
Data Index: 3385307 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0770. Min Act: -0.1700
Data Index: 3240639 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.1083. Min Act: -0.1700
Data Index: 1244230 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0770. Min Act: -0.1700
Data Index: 7934391 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0770. Min Act: -0.1700
Data Index: 7213122 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0770. Min Act: -0.1700
Data Index: 4795581 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0458. Min Act: -0.1700
Data Index: 4933359 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0458. Min Act: -0.1700
Data Index: 5387839 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0145. Min Act: -0.1700
Data Index: 1604416 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0145. Min Act: -0.1700
Data Index: 5465945 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0145. Min Act: -0.1700
Data Index: 7152799 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2333. Min Range: -5.2333
Max Act: 5.0145. Min Act: -0.1700
Data Index: 4575578 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2333. Min Range: -5.2333
Max Act: 4.9833. Min Act: -0.1700
Data Index: 3832086 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2333. Min Range: -5.2333
Max Act: 4.9833. Min Act: -0.1700
Data Index: 5339358 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2333. Min Range: -5.2333
Max Act: 4.9833. Min Act: -0.1700
Data Index: 3022113 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19