Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.3351. Min Act: -0.1698
Data Index: 167041 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.3175. Min Act: -0.1700
Data Index: 503413 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2998. Min Act: -0.1700
Data Index: 167040 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2645. Min Act: -0.1700
Data Index: 7912827 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2645. Min Act: -0.1700
Data Index: 2750427 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2469. Min Act: -0.1700
Data Index: 955022 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2293. Min Act: -0.1700
Data Index: 7569436 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2469. Min Act: -0.1700
Data Index: 3434129 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2469. Min Act: -0.1700
Data Index: 3399041 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2469. Min Act: -0.1700
Data Index: 1910278 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2469. Min Act: -0.1700
Data Index: 3425327 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2293. Min Act: -0.1700
Data Index: 8012793 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2293. Min Act: -0.1700
Data Index: 1916948 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2293. Min Act: -0.1700
Data Index: 1763678 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2293. Min Act: -0.1700
Data Index: 7020961 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2117. Min Act: -0.1700
Data Index: 4848378 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2117. Min Act: -0.1700
Data Index: 312859 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2117. Min Act: -0.1700
Data Index: 5016175 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2117. Min Act: -0.1700
Data Index: 5168222 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3351. Min Range: -1.3351
Max Act: 1.2117. Min Act: -0.1700
Data Index: 5755299 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19