Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.8138. Min Act: -0.1700
Data Index: 5359023 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.4076. Min Act: -0.1700
Data Index: 5815530 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.2513. Min Act: -0.1700
Data Index: 1040747 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.2826. Min Act: -0.1700
Data Index: 6708268 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.2513. Min Act: -0.1700
Data Index: 343898 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.2826. Min Act: -0.1700
Data Index: 5852967 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.1263. Min Act: -0.1700
Data Index: 8675525 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.0638. Min Act: -0.1700
Data Index: 3867954 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.0326. Min Act: -0.1700
Data Index: 5716988 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.0013. Min Act: -0.1700
Data Index: 7899553 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8138. Min Range: -7.8138
Max Act: 7.0013. Min Act: -0.1700
Data Index: 4048714 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8138. Min Range: -7.8138
Max Act: 6.9701. Min Act: -0.1700
Data Index: 2380963 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8138. Min Range: -7.8138
Max Act: 6.9388. Min Act: -0.1700
Data Index: 8573151 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8138. Min Range: -7.8138
Max Act: 6.8763. Min Act: -0.1700
Data Index: 2296395 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8138. Min Range: -7.8138
Max Act: 6.9076. Min Act: -0.1700
Data Index: 3811652 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8138. Min Range: -7.8138
Max Act: 6.8763. Min Act: -0.1700
Data Index: 2306266 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8138. Min Range: -7.8138
Max Act: 6.8763. Min Act: -0.1700
Data Index: 7138419 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8138. Min Range: -7.8138
Max Act: 6.8451. Min Act: -0.1700
Data Index: 158335 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8138. Min Range: -7.8138
Max Act: 6.8451. Min Act: -0.1700
Data Index: 810862 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8138. Min Range: -7.8138
Max Act: 6.8451. Min Act: -0.1700
Data Index: 1025939 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19