Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4265 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2997. Min Range: -6.2997
Max Act: 6.2997. Min Act: -0.1700
Data Index: 5628273 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2997. Min Range: -6.2997
Max Act: 6.0810. Min Act: -0.1700
Data Index: 5521385 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.9872. Min Act: -0.1700
Data Index: 3114203 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.9560. Min Act: -0.1700
Data Index: 2061189 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.9247. Min Act: -0.1700
Data Index: 2386604 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.8935. Min Act: -0.1700
Data Index: 3123480 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.8622. Min Act: -0.1700
Data Index: 7871997 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.8622. Min Act: -0.1700
Data Index: 8057301 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.8622. Min Act: -0.1700
Data Index: 342827 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.8310. Min Act: -0.1700
Data Index: 8635138 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.8310. Min Act: -0.1700
Data Index: 6200558 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.7997. Min Act: -0.1700
Data Index: 409197 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.7997. Min Act: -0.1700
Data Index: 4843559 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.7685. Min Act: -0.1700
Data Index: 1087857 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.7372. Min Act: -0.1700
Data Index: 4157290 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.7997. Min Act: -0.1700
Data Index: 4624977 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.7997. Min Act: -0.1700
Data Index: 591641 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.7997. Min Act: -0.1700
Data Index: 2905837 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.7372. Min Act: -0.1700
Data Index: 4508568 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2997. Min Range: -6.2997
Max Act: 5.7372. Min Act: -0.1700
Data Index: 1524092 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19