Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1484. Min Range: -4.1484
Max Act: 4.1484. Min Act: -0.1700
Data Index: 92849 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1484. Min Range: -4.1484
Max Act: 4.1172. Min Act: -0.1700
Data Index: 5982534 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1484. Min Range: -4.1484
Max Act: 4.0859. Min Act: -0.1700
Data Index: 6997308 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1484. Min Range: -4.1484
Max Act: 4.0546. Min Act: -0.1700
Data Index: 277049 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1484. Min Range: -4.1484
Max Act: 4.0546. Min Act: -0.1700
Data Index: 2854066 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1484. Min Range: -4.1484
Max Act: 4.0546. Min Act: -0.1700
Data Index: 2742541 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1484. Min Range: -4.1484
Max Act: 4.0234. Min Act: -0.1700
Data Index: 4597029 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1484. Min Range: -4.1484
Max Act: 4.0234. Min Act: -0.1700
Data Index: 4206424 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1484. Min Range: -4.1484
Max Act: 4.0234. Min Act: -0.1700
Data Index: 522750 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9921. Min Act: -0.1700
Data Index: 6363671 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9921. Min Act: -0.1700
Data Index: 8285650 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9609. Min Act: -0.1700
Data Index: 2275837 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9609. Min Act: -0.1700
Data Index: 7520671 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9609. Min Act: -0.1700
Data Index: 7245204 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9609. Min Act: -0.1700
Data Index: 5440284 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9296. Min Act: -0.1700
Data Index: 5673113 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9296. Min Act: -0.1700
Data Index: 4387239 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9296. Min Act: -0.1700
Data Index: 5212263 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9296. Min Act: -0.1700
Data Index: 393877 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1484. Min Range: -4.1484
Max Act: 3.9296. Min Act: -0.1700
Data Index: 3551531 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19