Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 736 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.9872. Min Act: -0.1700
Data Index: 8459032 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.9247. Min Act: -0.1700
Data Index: 2159681 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.8934. Min Act: -0.1700
Data Index: 134135 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.8309. Min Act: -0.1700
Data Index: 291534 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7997. Min Act: -0.1700
Data Index: 6437079 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7997. Min Act: -0.1700
Data Index: 3072302 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7997. Min Act: -0.1700
Data Index: 6583903 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.8309. Min Act: -0.1700
Data Index: 3077311 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7997. Min Act: -0.1700
Data Index: 8077127 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.8309. Min Act: -0.1700
Data Index: 4345746 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7684. Min Act: -0.1700
Data Index: 1345278 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7997. Min Act: -0.1700
Data Index: 1550595 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7997. Min Act: -0.1700
Data Index: 1057653 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7372. Min Act: -0.1700
Data Index: 5931985 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7372. Min Act: -0.1700
Data Index: 43567 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7059. Min Act: -0.1700
Data Index: 605820 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7372. Min Act: -0.1700
Data Index: 3566562 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7684. Min Act: -0.1700
Data Index: 1493232 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7372. Min Act: -0.1700
Data Index: 2881907 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9872. Min Range: -4.9872
Max Act: 4.7684. Min Act: -0.1700
Data Index: 4099014 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19