Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 466 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.4662. Min Act: -0.1700
Data Index: 5199715 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.3724. Min Act: -0.1700
Data Index: 6275897 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.2787. Min Act: -0.1700
Data Index: 3817455 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.2474. Min Act: -0.1700
Data Index: 306483 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1537. Min Act: -0.1700
Data Index: 5667731 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1537. Min Act: -0.1700
Data Index: 783846 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1537. Min Act: -0.1700
Data Index: 2028731 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1537. Min Act: -0.1700
Data Index: 2905810 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1224. Min Act: -0.1700
Data Index: 1599088 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1224. Min Act: -0.1700
Data Index: 4495051 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0912. Min Act: -0.1700
Data Index: 7021436 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1224. Min Act: -0.1700
Data Index: 7824619 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0912. Min Act: -0.1700
Data Index: 4408306 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0599. Min Act: -0.1700
Data Index: 8522824 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0599. Min Act: -0.1700
Data Index: 2209310 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0287. Min Act: -0.1700
Data Index: 1611556 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0287. Min Act: -0.1700
Data Index: 2188654 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0287. Min Act: -0.1700
Data Index: 6601275 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4662. Min Range: -5.4662
Max Act: 4.9974. Min Act: -0.1700
Data Index: 3543075 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4662. Min Range: -5.4662
Max Act: 4.9974. Min Act: -0.1700
Data Index: 6676939 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19