Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.7244. Min Act: -0.1700
Data Index: 1944333 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5681. Min Act: -0.1700
Data Index: 3394003 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5369. Min Act: -0.1700
Data Index: 1447477 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4744. Min Act: -0.1700
Data Index: 4894024 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.3181. Min Act: -0.1700
Data Index: 4198265 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.2556. Min Act: -0.1700
Data Index: 6279237 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0994. Min Act: -0.1700
Data Index: 4999783 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.1306. Min Act: -0.1700
Data Index: 7130136 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0994. Min Act: -0.1700
Data Index: 5126573 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0994. Min Act: -0.1700
Data Index: 2861413 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0681. Min Act: -0.1700
Data Index: 2736883 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0681. Min Act: -0.1700
Data Index: 7317098 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0369. Min Act: -0.1700
Data Index: 8515502 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0369. Min Act: -0.1700
Data Index: 1643581 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0369. Min Act: -0.1700
Data Index: 5039188 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0369. Min Act: -0.1700
Data Index: 2649343 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0681. Min Act: -0.1700
Data Index: 6523137 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0056. Min Act: -0.1700
Data Index: 6163481 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7244. Min Range: -6.7244
Max Act: 5.9744. Min Act: -0.1700
Data Index: 3664282 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.0056. Min Act: -0.1700
Data Index: 4125271 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19