Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3725 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3444. Min Range: -6.3444
Max Act: 6.3444. Min Act: -0.1700
Data Index: 2570315 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3444. Min Range: -6.3444
Max Act: 6.1881. Min Act: -0.1700
Data Index: 772874 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3444. Min Range: -6.3444
Max Act: 6.1256. Min Act: -0.1700
Data Index: 3939242 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3444. Min Range: -6.3444
Max Act: 6.1256. Min Act: -0.1700
Data Index: 772859 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3444. Min Range: -6.3444
Max Act: 6.0631. Min Act: -0.1700
Data Index: 772856 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3444. Min Range: -6.3444
Max Act: 6.0631. Min Act: -0.1700
Data Index: 772860 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3444. Min Range: -6.3444
Max Act: 6.0319. Min Act: -0.1700
Data Index: 4920072 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3444. Min Range: -6.3444
Max Act: 6.0006. Min Act: -0.1700
Data Index: 772857 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.9694. Min Act: -0.1700
Data Index: 8089820 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.9381. Min Act: -0.1700
Data Index: 772866 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.9381. Min Act: -0.1700
Data Index: 3985264 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.9381. Min Act: -0.1700
Data Index: 8615309 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.9381. Min Act: -0.1700
Data Index: 3985263 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.8756. Min Act: -0.1700
Data Index: 1379217 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.8444. Min Act: -0.1700
Data Index: 1561635 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.8444. Min Act: -0.1700
Data Index: 3985260 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.8131. Min Act: -0.1700
Data Index: 2231061 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.8131. Min Act: -0.1700
Data Index: 3331202 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.7819. Min Act: -0.1700
Data Index: 3331205 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3444. Min Range: -6.3444
Max Act: 5.7819. Min Act: -0.1700
Data Index: 4789501 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19