Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0112. Min Range: -7.0112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 6361278 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0112. Min Range: -7.0112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 1772700 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0112. Min Range: -7.0112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 2929678 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0112. Min Range: -7.0112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 4353996 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0112. Min Range: -7.0112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 7405468 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.9799. Min Act: -0.1700
Data Index: 1429323 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0112. Min Range: -7.0112
Max Act: 7.0112. Min Act: -0.1700
Data Index: 289402 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.9799. Min Act: -0.1700
Data Index: 6941399 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.9799. Min Act: -0.1700
Data Index: 3731405 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.9487. Min Act: -0.1700
Data Index: 2170857 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.9487. Min Act: -0.1700
Data Index: 569995 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.9174. Min Act: -0.1700
Data Index: 3177653 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.9174. Min Act: -0.1700
Data Index: 7136208 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.8549. Min Act: -0.1700
Data Index: 135920 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.8862. Min Act: -0.1700
Data Index: 3908656 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.8862. Min Act: -0.1700
Data Index: 6919024 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.8862. Min Act: -0.1700
Data Index: 5579453 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.8549. Min Act: -0.1700
Data Index: 1576136 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.8549. Min Act: -0.1700
Data Index: 2064829 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0112. Min Range: -7.0112
Max Act: 6.8862. Min Act: -0.1700
Data Index: 5799182 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19