Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2347 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.7386. Min Act: -0.1700
Data Index: 2537807 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.7386. Min Act: -0.1700
Data Index: 5329804 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.3636. Min Act: -0.1700
Data Index: 183796 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.1761. Min Act: -0.1700
Data Index: 4667253 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.1136. Min Act: -0.1700
Data Index: 5140038 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.1136. Min Act: -0.1700
Data Index: 6891842 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.1136. Min Act: -0.1700
Data Index: 6465572 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.0511. Min Act: -0.1700
Data Index: 4785744 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.0511. Min Act: -0.1700
Data Index: 8201308 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.0511. Min Act: -0.1700
Data Index: 1549440 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7386. Min Range: -9.7386
Max Act: 9.0511. Min Act: -0.1700
Data Index: 2531718 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7386. Min Range: -9.7386
Max Act: 8.9261. Min Act: -0.1700
Data Index: 3145669 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7386. Min Range: -9.7386
Max Act: 8.9261. Min Act: -0.1700
Data Index: 4903591 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7386. Min Range: -9.7386
Max Act: 8.9261. Min Act: -0.1700
Data Index: 4841920 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7386. Min Range: -9.7386
Max Act: 8.8636. Min Act: -0.1700
Data Index: 4619578 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7386. Min Range: -9.7386
Max Act: 8.8636. Min Act: -0.1700
Data Index: 3145670 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7386. Min Range: -9.7386
Max Act: 8.8636. Min Act: -0.1700
Data Index: 4097910 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7386. Min Range: -9.7386
Max Act: 8.8011. Min Act: -0.1700
Data Index: 1886676 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7386. Min Range: -9.7386
Max Act: 8.8011. Min Act: -0.1700
Data Index: 852549 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7386. Min Range: -9.7386
Max Act: 8.7386. Min Act: -0.1700
Data Index: 7353445 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19