Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.5631. Min Act: -0.1700
Data Index: 217624 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.5631. Min Act: -0.1700
Data Index: 7052078 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.5318. Min Act: -0.1700
Data Index: 8554960 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.5318. Min Act: -0.1700
Data Index: 7632524 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.5006. Min Act: -0.1700
Data Index: 7632521 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.4068. Min Act: -0.1700
Data Index: 4180236 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.4068. Min Act: -0.1700
Data Index: 8475473 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3756. Min Act: -0.1700
Data Index: 848095 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3756. Min Act: -0.1700
Data Index: 7052079 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3756. Min Act: -0.1700
Data Index: 2350862 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3443. Min Act: -0.1700
Data Index: 5526084 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3443. Min Act: -0.1700
Data Index: 1736859 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3443. Min Act: -0.1700
Data Index: 7632525 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3131. Min Act: -0.1700
Data Index: 7632519 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3443. Min Act: -0.1697
Data Index: 2096964 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3131. Min Act: -0.1700
Data Index: 848099 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3131. Min Act: -0.1700
Data Index: 1713117 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3131. Min Act: -0.1700
Data Index: 5129665 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3131. Min Act: -0.1700
Data Index: 379411 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5631. Min Range: -4.5631
Max Act: 4.3131. Min Act: -0.1700
Data Index: 8715398 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19