Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 631 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.7570. Min Act: -0.1700
Data Index: 3636819 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.6945. Min Act: -0.1700
Data Index: 853798 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.6632. Min Act: -0.1700
Data Index: 3582873 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.6007. Min Act: -0.1700
Data Index: 2465712 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.5070. Min Act: -0.1700
Data Index: 4307401 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.4757. Min Act: -0.1700
Data Index: 1498460 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.4445. Min Act: -0.1700
Data Index: 7836399 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.4445. Min Act: -0.1700
Data Index: 1042140 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.3820. Min Act: -0.1700
Data Index: 4276280 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.3820. Min Act: -0.1700
Data Index: 7261998 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.3507. Min Act: -0.1700
Data Index: 1219700 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.3507. Min Act: -0.1700
Data Index: 1514823 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.3820. Min Act: -0.1700
Data Index: 7069313 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.3507. Min Act: -0.1700
Data Index: 5978837 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.3195. Min Act: -0.1700
Data Index: 2389016 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.3195. Min Act: -0.1700
Data Index: 3941397 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.2882. Min Act: -0.1700
Data Index: 4628411 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.2570. Min Act: -0.1700
Data Index: 2389007 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.2570. Min Act: -0.1700
Data Index: 6198067 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7570. Min Range: -6.7570
Max Act: 6.2257. Min Act: -0.1700
Data Index: 3121529 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19