Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 607 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.7124. Min Range: -13.7124
Max Act: 13.7124. Min Act: -0.1700
Data Index: 7491999 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.7124. Min Range: -13.7124
Max Act: 13.3374. Min Act: -0.1700
Data Index: 4403064 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.7124. Min Range: -13.7124
Max Act: 13.2124. Min Act: -0.1700
Data Index: 5411104 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.8374. Min Act: -0.1700
Data Index: 3676161 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.6499. Min Act: -0.1700
Data Index: 4626499 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.4624. Min Act: -0.1700
Data Index: 461742 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.3374. Min Act: -0.1700
Data Index: 3775520 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.3999. Min Act: -0.1700
Data Index: 2204294 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.2749. Min Act: -0.1700
Data Index: 2922477 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.2749. Min Act: -0.1700
Data Index: 7566412 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.2749. Min Act: -0.1700
Data Index: 1346515 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.1499. Min Act: -0.1700
Data Index: 7608915 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.0249. Min Act: -0.1700
Data Index: 7965449 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.0249. Min Act: -0.1700
Data Index: 6031542 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.7124. Min Range: -13.7124
Max Act: 11.9624. Min Act: -0.1700
Data Index: 232882 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.7124. Min Range: -13.7124
Max Act: 11.9624. Min Act: -0.1700
Data Index: 5582163 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.7124. Min Range: -13.7124
Max Act: 12.0249. Min Act: -0.1700
Data Index: 2770263 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.7124. Min Range: -13.7124
Max Act: 11.8374. Min Act: -0.1700
Data Index: 4441999 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.7124. Min Range: -13.7124
Max Act: 11.9624. Min Act: -0.1700
Data Index: 2294248 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.7124. Min Range: -13.7124
Max Act: 11.8999. Min Act: -0.1700
Data Index: 369921 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19