Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4796. Min Range: -8.4796
Max Act: 8.4796. Min Act: -0.1700
Data Index: 7415623 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4796. Min Range: -8.4796
Max Act: 8.4796. Min Act: -0.1700
Data Index: 349941 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4796. Min Range: -8.4796
Max Act: 8.3546. Min Act: -0.1700
Data Index: 3921206 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4796. Min Range: -8.4796
Max Act: 8.2296. Min Act: -0.1700
Data Index: 7894719 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4796. Min Range: -8.4796
Max Act: 8.1671. Min Act: -0.1700
Data Index: 798277 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4796. Min Range: -8.4796
Max Act: 8.0421. Min Act: -0.1700
Data Index: 2350942 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.9796. Min Act: -0.1700
Data Index: 6426947 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.9796. Min Act: -0.1700
Data Index: 155228 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.9171. Min Act: -0.1700
Data Index: 1463573 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.9171. Min Act: -0.1700
Data Index: 3958111 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.8858. Min Act: -0.1700
Data Index: 1482774 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.9171. Min Act: -0.1700
Data Index: 5186887 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.8858. Min Act: -0.1700
Data Index: 1959318 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.8233. Min Act: -0.1700
Data Index: 1129697 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.8233. Min Act: -0.1700
Data Index: 5070411 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.8233. Min Act: -0.1700
Data Index: 3697792 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.8233. Min Act: -0.1700
Data Index: 3664557 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.7608. Min Act: -0.1700
Data Index: 7719988 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.7921. Min Act: -0.1700
Data Index: 1614424 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4796. Min Range: -8.4796
Max Act: 7.7608. Min Act: -0.1700
Data Index: 8278573 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19