Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 457 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0923. Min Range: -3.0923
Max Act: 3.0923. Min Act: -0.1700
Data Index: 7963930 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9976. Min Act: -0.1700
Data Index: 5683239 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9818. Min Act: -0.1700
Data Index: 4862165 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9818. Min Act: -0.1700
Data Index: 6434812 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9343. Min Act: -0.1700
Data Index: 3186630 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9343. Min Act: -0.1700
Data Index: 3987117 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9343. Min Act: -0.1700
Data Index: 634660 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9185. Min Act: -0.1700
Data Index: 4206113 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9185. Min Act: -0.1700
Data Index: 4580958 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9026. Min Act: -0.1700
Data Index: 2769578 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9026. Min Act: -0.1700
Data Index: 8225112 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9026. Min Act: -0.1700
Data Index: 3090419 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9026. Min Act: -0.1700
Data Index: 8516223 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.9026. Min Act: -0.1700
Data Index: 88149 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.8709. Min Act: -0.1700
Data Index: 2207783 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.8709. Min Act: -0.1700
Data Index: 5943201 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.8550. Min Act: -0.1700
Data Index: 5913112 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.8709. Min Act: -0.1700
Data Index: 320280 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.8709. Min Act: -0.1700
Data Index: 5911712 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0923. Min Range: -3.0923
Max Act: 2.8550. Min Act: -0.1700
Data Index: 3509236 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19