Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.7507. Min Act: -0.1700
Data Index: 4716360 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.5942. Min Act: -0.1700
Data Index: 6068009 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.5942. Min Act: -0.1698
Data Index: 5380609 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.5316. Min Act: -0.1699
Data Index: 5202557 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.5003. Min Act: -0.1700
Data Index: 5117252 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.5003. Min Act: -0.1700
Data Index: 332544 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.5003. Min Act: -0.1700
Data Index: 2651220 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4690. Min Act: -0.1699
Data Index: 6194615 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4690. Min Act: -0.1698
Data Index: 6208385 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4690. Min Act: -0.1690
Data Index: 8304525 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4690. Min Act: -0.1680
Data Index: 339236 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4690. Min Act: -0.1686
Data Index: 1460176 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4376. Min Act: -0.1700
Data Index: 5143398 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4376. Min Act: -0.1664
Data Index: 686214 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4376. Min Act: -0.1628
Data Index: 6831683 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4063. Min Act: -0.1700
Data Index: 4546818 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4063. Min Act: -0.1700
Data Index: 5178356 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.3749. Min Act: -0.1700
Data Index: 5605407 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4063. Min Act: -0.1700
Data Index: 1036108 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7507. Min Range: -3.7507
Max Act: 3.4063. Min Act: -0.1694
Data Index: 164383 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19