Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.6451. Min Act: -0.1700
Data Index: 1406199 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.5042. Min Act: -0.1700
Data Index: 7419554 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.4258. Min Act: -0.1700
Data Index: 434335 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3945. Min Act: -0.1700
Data Index: 6939228 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3631. Min Act: -0.1700
Data Index: 7854457 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3631. Min Act: -0.1700
Data Index: 168112 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3474. Min Act: -0.1700
Data Index: 7677087 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3317. Min Act: -0.1700
Data Index: 394620 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3317. Min Act: -0.1700
Data Index: 6134539 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3317. Min Act: -0.1700
Data Index: 6364851 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3160. Min Act: -0.1700
Data Index: 2737336 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3160. Min Act: -0.1700
Data Index: 2978062 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3160. Min Act: -0.1700
Data Index: 1309322 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3160. Min Act: -0.1700
Data Index: 1715921 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3160. Min Act: -0.1700
Data Index: 1823670 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3003. Min Act: -0.1700
Data Index: 4198984 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.3003. Min Act: -0.1700
Data Index: 4003725 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.2846. Min Act: -0.1700
Data Index: 6601474 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.2846. Min Act: -0.1700
Data Index: 4449634 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6451. Min Range: -3.6451
Max Act: 3.2846. Min Act: -0.1700
Data Index: 8801651 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19