Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1747 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2099. Min Range: -5.2099
Max Act: 5.2099. Min Act: -0.1700
Data Index: 6676585 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2099. Min Range: -5.2099
Max Act: 5.1474. Min Act: -0.1700
Data Index: 6434667 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2099. Min Range: -5.2099
Max Act: 5.1162. Min Act: -0.1700
Data Index: 4519798 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2099. Min Range: -5.2099
Max Act: 5.0849. Min Act: -0.1700
Data Index: 1926279 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2099. Min Range: -5.2099
Max Act: 5.0537. Min Act: -0.1700
Data Index: 5953287 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2099. Min Range: -5.2099
Max Act: 5.0224. Min Act: -0.1700
Data Index: 1329065 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2099. Min Range: -5.2099
Max Act: 5.0224. Min Act: -0.1700
Data Index: 5322211 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9912. Min Act: -0.1700
Data Index: 141170 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9912. Min Act: -0.1700
Data Index: 5239643 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9912. Min Act: -0.1700
Data Index: 5198436 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9599. Min Act: -0.1700
Data Index: 8483828 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9599. Min Act: -0.1700
Data Index: 4929437 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9287. Min Act: -0.1700
Data Index: 2381467 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9287. Min Act: -0.1700
Data Index: 8419455 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9287. Min Act: -0.1700
Data Index: 8241620 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9287. Min Act: -0.1700
Data Index: 6232678 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9287. Min Act: -0.1700
Data Index: 672431 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.9287. Min Act: -0.1700
Data Index: 91244 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.8974. Min Act: -0.1700
Data Index: 2041625 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2099. Min Range: -5.2099
Max Act: 4.8974. Min Act: -0.1700
Data Index: 21180 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19