Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 262 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.8443. Min Act: -0.1700
Data Index: 3721537 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.8443. Min Act: -0.1700
Data Index: 5709067 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.8131. Min Act: -0.1700
Data Index: 2767145 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.7818. Min Act: -0.1700
Data Index: 2605042 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.7506. Min Act: -0.1700
Data Index: 3878 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2951030 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6881. Min Act: -0.1700
Data Index: 7930529 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6881. Min Act: -0.1700
Data Index: 5567740 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6881. Min Act: -0.1700
Data Index: 1080062 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6881. Min Act: -0.1700
Data Index: 4772068 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6881. Min Act: -0.1700
Data Index: 7014544 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6881. Min Act: -0.1700
Data Index: 3648547 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6881. Min Act: -0.1700
Data Index: 7014552 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6568. Min Act: -0.1700
Data Index: 5525235 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6256. Min Act: -0.1700
Data Index: 5525234 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6568. Min Act: -0.1700
Data Index: 2782373 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6568. Min Act: -0.1700
Data Index: 2767146 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6568. Min Act: -0.1700
Data Index: 6833711 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6568. Min Act: -0.1700
Data Index: 2916930 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8443. Min Range: -5.8443
Max Act: 5.6568. Min Act: -0.1700
Data Index: 3806474 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19