Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6387 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.4976. Min Act: -0.1700
Data Index: 4895189 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.4663. Min Act: -0.1700
Data Index: 8774639 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.3101. Min Act: -0.1700
Data Index: 6861043 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.2788. Min Act: -0.1700
Data Index: 5026152 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.2163. Min Act: -0.1700
Data Index: 7632597 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.1226. Min Act: -0.1700
Data Index: 3453778 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.1226. Min Act: -0.1700
Data Index: 2425730 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.0913. Min Act: -0.1700
Data Index: 1866184 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.0601. Min Act: -0.1700
Data Index: 4637370 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.0288. Min Act: -0.1700
Data Index: 4979302 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.0288. Min Act: -0.1700
Data Index: 2333491 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.0288. Min Act: -0.1700
Data Index: 2149105 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4976. Min Range: -7.4976
Max Act: 6.9976. Min Act: -0.1700
Data Index: 3046578 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4976. Min Range: -7.4976
Max Act: 7.0288. Min Act: -0.1700
Data Index: 6087485 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4976. Min Range: -7.4976
Max Act: 6.9663. Min Act: -0.1700
Data Index: 1264222 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4976. Min Range: -7.4976
Max Act: 6.9976. Min Act: -0.1700
Data Index: 1083996 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4976. Min Range: -7.4976
Max Act: 6.9976. Min Act: -0.1700
Data Index: 8633370 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4976. Min Range: -7.4976
Max Act: 6.9663. Min Act: -0.1700
Data Index: 939574 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4976. Min Range: -7.4976
Max Act: 6.9976. Min Act: -0.1700
Data Index: 659585 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4976. Min Range: -7.4976
Max Act: 6.9663. Min Act: -0.1700
Data Index: 7356621 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19