Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1683 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1757. Min Range: -6.1757
Max Act: 6.1757. Min Act: -0.1700
Data Index: 6085543 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1757. Min Range: -6.1757
Max Act: 6.0819. Min Act: -0.1700
Data Index: 963242 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1757. Min Range: -6.1757
Max Act: 6.0507. Min Act: -0.1700
Data Index: 7184232 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1757. Min Range: -6.1757
Max Act: 6.0507. Min Act: -0.1700
Data Index: 6666835 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.9882. Min Act: -0.1700
Data Index: 7406950 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.9569. Min Act: -0.1700
Data Index: 7406949 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.9569. Min Act: -0.1700
Data Index: 6282593 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.9569. Min Act: -0.1700
Data Index: 6696857 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.9257. Min Act: -0.1700
Data Index: 628407 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.9257. Min Act: -0.1700
Data Index: 1210806 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.9257. Min Act: -0.1700
Data Index: 7387991 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.8944. Min Act: -0.1700
Data Index: 2818319 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.9257. Min Act: -0.1700
Data Index: 7826759 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.8944. Min Act: -0.1700
Data Index: 3302965 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.8632. Min Act: -0.1700
Data Index: 2350290 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.8632. Min Act: -0.1700
Data Index: 3111076 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.8632. Min Act: -0.1700
Data Index: 7406948 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.8319. Min Act: -0.1700
Data Index: 7017560 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.8632. Min Act: -0.1700
Data Index: 7388000 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1757. Min Range: -6.1757
Max Act: 5.8319. Min Act: -0.1700
Data Index: 4134802 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19