Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4803 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.3325. Min Act: -0.1700
Data Index: 5262313 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.2388. Min Act: -0.1700
Data Index: 750323 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.1763. Min Act: -0.1700
Data Index: 5015437 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.1450. Min Act: -0.1700
Data Index: 4842309 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.1450. Min Act: -0.1700
Data Index: 3699601 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.1138. Min Act: -0.1700
Data Index: 595014 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.0825. Min Act: -0.1700
Data Index: 5318921 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.0200. Min Act: -0.1700
Data Index: 329189 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.0513. Min Act: -0.1700
Data Index: 4931413 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3325. Min Range: -5.3325
Max Act: 5.0200. Min Act: -0.1700
Data Index: 7503785 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.9888. Min Act: -0.1700
Data Index: 5378212 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.9888. Min Act: -0.1700
Data Index: 7051475 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.9888. Min Act: -0.1700
Data Index: 3931441 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.9575. Min Act: -0.1700
Data Index: 6736166 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.9263. Min Act: -0.1700
Data Index: 2586721 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.9263. Min Act: -0.1700
Data Index: 2332459 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.9263. Min Act: -0.1700
Data Index: 8024424 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.9263. Min Act: -0.1700
Data Index: 1955549 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.8950. Min Act: -0.1700
Data Index: 6113584 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3325. Min Range: -5.3325
Max Act: 4.8638. Min Act: -0.1700
Data Index: 2019534 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19