Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1970 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4006. Min Range: -7.4006
Max Act: 7.4006. Min Act: -0.1700
Data Index: 3109316 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.9006. Min Act: -0.1700
Data Index: 2316405 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.7444. Min Act: -0.1700
Data Index: 8710860 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.6506. Min Act: -0.1700
Data Index: 3700897 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.5881. Min Act: -0.1700
Data Index: 4723192 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.5881. Min Act: -0.1700
Data Index: 4988980 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.5569. Min Act: -0.1700
Data Index: 8677529 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.4944. Min Act: -0.1700
Data Index: 7313457 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.0256. Min Act: -0.1700
Data Index: 3357082 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.0256. Min Act: -0.1700
Data Index: 6156161 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4006. Min Range: -7.4006
Max Act: 6.0256. Min Act: -0.1700
Data Index: 574552 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4006. Min Range: -7.4006
Max Act: 5.9631. Min Act: -0.1700
Data Index: 5510733 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4006. Min Range: -7.4006
Max Act: 5.9631. Min Act: -0.1700
Data Index: 2102694 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4006. Min Range: -7.4006
Max Act: 5.9319. Min Act: -0.1700
Data Index: 5745109 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4006. Min Range: -7.4006
Max Act: 5.9006. Min Act: -0.1700
Data Index: 219434 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4006. Min Range: -7.4006
Max Act: 5.8381. Min Act: -0.1700
Data Index: 388707 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4006. Min Range: -7.4006
Max Act: 5.8069. Min Act: -0.1700
Data Index: 4207077 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4006. Min Range: -7.4006
Max Act: 5.8381. Min Act: -0.1700
Data Index: 2733801 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4006. Min Range: -7.4006
Max Act: 5.7131. Min Act: -0.1700
Data Index: 6791147 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4006. Min Range: -7.4006
Max Act: 5.7444. Min Act: -0.1700
Data Index: 6630886 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19