Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1208 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.1527. Min Act: -0.1700
Data Index: 5285193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.1527. Min Act: -0.1700
Data Index: 1180375 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.1527. Min Act: -0.1700
Data Index: 2863158 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.1527. Min Act: -0.1700
Data Index: 2736596 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 798629 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.1214. Min Act: -0.1700
Data Index: 8046864 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.1214. Min Act: -0.1700
Data Index: 1107050 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.1214. Min Act: -0.1700
Data Index: 6617266 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.1214. Min Act: -0.1700
Data Index: 6178106 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.1214. Min Act: -0.1700
Data Index: 5352107 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 695654 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 6263982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 2724975 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 5959943 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 1827212 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 6636070 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 7500250 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 4339489 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 2234919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1527. Min Range: -4.1527
Max Act: 4.0902. Min Act: -0.1700
Data Index: 3903973 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19