Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 75 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.7256. Min Act: -0.1700
Data Index: 8298473 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.5068. Min Act: -0.1700
Data Index: 318060 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.4443. Min Act: -0.1700
Data Index: 2386576 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.3193. Min Act: -0.1700
Data Index: 8496576 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.3193. Min Act: -0.1700
Data Index: 4399312 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.2256. Min Act: -0.1700
Data Index: 7132683 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.2256. Min Act: -0.1700
Data Index: 7358958 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.2256. Min Act: -0.1700
Data Index: 8499419 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.2256. Min Act: -0.1700
Data Index: 5323760 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.1943. Min Act: -0.1700
Data Index: 7229222 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.1943. Min Act: -0.1700
Data Index: 6049028 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.1943. Min Act: -0.1700
Data Index: 7591068 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.1631. Min Act: -0.1700
Data Index: 1058385 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.1318. Min Act: -0.1700
Data Index: 4501255 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.1318. Min Act: -0.1700
Data Index: 7849120 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.1006. Min Act: -0.1700
Data Index: 4748584 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.0693. Min Act: -0.1700
Data Index: 986766 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.0693. Min Act: -0.1700
Data Index: 4645010 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.0381. Min Act: -0.1700
Data Index: 7386127 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7256. Min Range: -6.7256
Max Act: 5.9756. Min Act: -0.1700
Data Index: 7203209 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19