Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.4037. Min Act: -0.1700
Data Index: 4636587 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.3873. Min Act: -0.1700
Data Index: 5241567 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.3873. Min Act: -0.1700
Data Index: 603093 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.3710. Min Act: -0.1700
Data Index: 5897223 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.3218. Min Act: -0.1700
Data Index: 3550686 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.3054. Min Act: -0.1700
Data Index: 6517153 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.3054. Min Act: -0.1700
Data Index: 1927008 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.3054. Min Act: -0.1700
Data Index: 6948129 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2889. Min Act: -0.1700
Data Index: 4528291 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2889. Min Act: -0.1700
Data Index: 5949871 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.3054. Min Act: -0.1700
Data Index: 4859878 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2889. Min Act: -0.1700
Data Index: 2352388 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2889. Min Act: -0.1700
Data Index: 2451854 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2724. Min Act: -0.1700
Data Index: 1728984 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2724. Min Act: -0.1700
Data Index: 4314810 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2559. Min Act: -0.1700
Data Index: 4942232 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2724. Min Act: -0.1700
Data Index: 6698285 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2724. Min Act: -0.1700
Data Index: 1979129 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2559. Min Act: -0.1700
Data Index: 4859879 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4037. Min Range: -2.4037
Max Act: 2.2559. Min Act: -0.1700
Data Index: 4948768 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19