Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.3276. Min Act: -0.1700
Data Index: 5609735 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.3119. Min Act: -0.1700
Data Index: 7658857 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2962. Min Act: -0.1700
Data Index: 4355746 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2805. Min Act: -0.1700
Data Index: 4089584 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2962. Min Act: -0.1700
Data Index: 782323 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2648. Min Act: -0.1700
Data Index: 583131 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2648. Min Act: -0.1700
Data Index: 3027415 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2648. Min Act: -0.1700
Data Index: 7293542 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2334. Min Act: -0.1700
Data Index: 1321447 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2491. Min Act: -0.1700
Data Index: 451042 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2334. Min Act: -0.1700
Data Index: 1118456 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2334. Min Act: -0.1700
Data Index: 1411408 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2334. Min Act: -0.1700
Data Index: 2463555 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2334. Min Act: -0.1700
Data Index: 4809642 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2334. Min Act: -0.1700
Data Index: 763764 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2334. Min Act: -0.1700
Data Index: 6175258 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2020. Min Act: -0.1700
Data Index: 5317216 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2177. Min Act: -0.1700
Data Index: 2571371 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2177. Min Act: -0.1700
Data Index: 3214913 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3276. Min Range: -3.3276
Max Act: 3.2177. Min Act: -0.1700
Data Index: 5477875 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19