Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.5184. Min Act: -0.1700
Data Index: 8406829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.4369. Min Act: -0.1700
Data Index: 2440087 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.4296. Min Act: -0.1700
Data Index: 5820352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.4225. Min Act: -0.1700
Data Index: 1239478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.4082. Min Act: -0.1700
Data Index: 1682281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.3731. Min Act: -0.1700
Data Index: 7896973 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.3525. Min Act: -0.1700
Data Index: 6911626 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.3457. Min Act: -0.1700
Data Index: 8584951 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.3322. Min Act: -0.1699
Data Index: 7323259 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.3189. Min Act: -0.1700
Data Index: 83216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.3256. Min Act: -0.1700
Data Index: 237390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.3057. Min Act: -0.1700
Data Index: 1048436 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.2992. Min Act: -0.1700
Data Index: 7767454 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.2927. Min Act: -0.1700
Data Index: 956541 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.2927. Min Act: -0.1700
Data Index: 4175205 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.2799. Min Act: -0.1700
Data Index: 3115249 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.2735. Min Act: -0.1700
Data Index: 8504484 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.2799. Min Act: -0.1700
Data Index: 8544117 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.2863. Min Act: -0.1700
Data Index: 4024796 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5184. Min Range: -0.5184
Max Act: 0.2799. Min Act: -0.1700
Data Index: 5497166 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19