Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.4129. Min Act: -0.1700
Data Index: 3381478 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.3817. Min Act: -0.1700
Data Index: 3585075 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.3817. Min Act: -0.1700
Data Index: 3810901 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.3817. Min Act: -0.1700
Data Index: 6073083 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.3192. Min Act: -0.1700
Data Index: 4439988 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.2879. Min Act: -0.1700
Data Index: 1700545 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.2879. Min Act: -0.1700
Data Index: 4273434 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.2254. Min Act: -0.1700
Data Index: 4919929 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.2567. Min Act: -0.1700
Data Index: 3087951 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.2567. Min Act: -0.1700
Data Index: 2655163 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.2254. Min Act: -0.1700
Data Index: 7863433 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.1942. Min Act: -0.1700
Data Index: 5327848 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.1942. Min Act: -0.1700
Data Index: 201748 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.1942. Min Act: -0.1700
Data Index: 3599171 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.1942. Min Act: -0.1700
Data Index: 2259774 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.1942. Min Act: -0.1700
Data Index: 3501879 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.1629. Min Act: -0.1700
Data Index: 4526417 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.1317. Min Act: -0.1700
Data Index: 6590924 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.1317. Min Act: -0.1700
Data Index: 2721347 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4129. Min Range: -4.4129
Max Act: 4.1629. Min Act: -0.1700
Data Index: 3995136 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19