Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3287 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3240. Min Range: -5.3240
Max Act: 5.3240. Min Act: -0.1700
Data Index: 998432 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3240. Min Range: -5.3240
Max Act: 5.0115. Min Act: -0.1700
Data Index: 7019279 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3240. Min Range: -5.3240
Max Act: 5.0427. Min Act: -0.1700
Data Index: 8679096 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3240. Min Range: -5.3240
Max Act: 5.0115. Min Act: -0.1700
Data Index: 7050076 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.9802. Min Act: -0.1700
Data Index: 6755090 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.9802. Min Act: -0.1700
Data Index: 2684910 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.9177. Min Act: -0.1700
Data Index: 5834067 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8865. Min Act: -0.1700
Data Index: 7152738 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8865. Min Act: -0.1700
Data Index: 6913304 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8865. Min Act: -0.1700
Data Index: 5590283 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8865. Min Act: -0.1700
Data Index: 4337973 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8552. Min Act: -0.1700
Data Index: 6466440 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8552. Min Act: -0.1700
Data Index: 3260044 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8552. Min Act: -0.1700
Data Index: 5237205 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8240. Min Act: -0.1700
Data Index: 5698390 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8240. Min Act: -0.1700
Data Index: 5779376 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.7927. Min Act: -0.1700
Data Index: 4660595 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.7927. Min Act: -0.1700
Data Index: 413503 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.8240. Min Act: -0.1700
Data Index: 8635727 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3240. Min Range: -5.3240
Max Act: 4.7927. Min Act: -0.1700
Data Index: 2080357 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19