Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.7139. Min Act: -0.1699
Data Index: 4465328 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6965. Min Act: -0.1700
Data Index: 4617639 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6965. Min Act: -0.1700
Data Index: 6530182 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6965. Min Act: -0.1700
Data Index: 8386640 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6792. Min Act: -0.1700
Data Index: 4532711 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6531. Min Act: -0.1683
Data Index: 7476446 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6705. Min Act: -0.1699
Data Index: 3151098 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6618. Min Act: -0.1700
Data Index: 3060485 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6531. Min Act: -0.1700
Data Index: 344569 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6444. Min Act: -0.1700
Data Index: 8158469 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6531. Min Act: -0.1700
Data Index: 7191822 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6444. Min Act: -0.1700
Data Index: 2143314 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6444. Min Act: -0.1699
Data Index: 8386636 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6531. Min Act: -0.1700
Data Index: 4429990 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6357. Min Act: -0.1700
Data Index: 1375373 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6444. Min Act: -0.1700
Data Index: 3142046 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6357. Min Act: -0.1700
Data Index: 3880203 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6357. Min Act: -0.1700
Data Index: 2440020 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6357. Min Act: -0.1700
Data Index: 6417314 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7139. Min Range: -1.7139
Max Act: 1.6444. Min Act: -0.1700
Data Index: 3542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19