Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.6701. Min Act: -0.1700
Data Index: 5971535 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.6388. Min Act: -0.1700
Data Index: 785527 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.5763. Min Act: -0.1700
Data Index: 3460955 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.5451. Min Act: -0.1700
Data Index: 3907664 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.5451. Min Act: -0.1700
Data Index: 5824313 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.5451. Min Act: -0.1700
Data Index: 431591 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.5138. Min Act: -0.1700
Data Index: 4921762 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4826. Min Act: -0.1700
Data Index: 5304511 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4513. Min Act: -0.1700
Data Index: 8415611 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4513. Min Act: -0.1700
Data Index: 3721647 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4513. Min Act: -0.1700
Data Index: 3325429 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4513. Min Act: -0.1700
Data Index: 1441908 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4513. Min Act: -0.1700
Data Index: 8107770 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4513. Min Act: -0.1700
Data Index: 1386351 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4513. Min Act: -0.1700
Data Index: 561915 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4201. Min Act: -0.1700
Data Index: 5952900 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4513. Min Act: -0.1700
Data Index: 4743419 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4826. Min Act: -0.1700
Data Index: 847365 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4201. Min Act: -0.1700
Data Index: 5621311 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6701. Min Range: -5.6701
Max Act: 5.4201. Min Act: -0.1700
Data Index: 5861777 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19