Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4583 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3107. Min Range: -8.3107
Max Act: 8.3107. Min Act: -0.1700
Data Index: 4722514 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3107. Min Range: -8.3107
Max Act: 8.3107. Min Act: -0.1700
Data Index: 2387726 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3107. Min Range: -8.3107
Max Act: 8.2482. Min Act: -0.1700
Data Index: 3710406 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3107. Min Range: -8.3107
Max Act: 8.1232. Min Act: -0.1700
Data Index: 663819 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3107. Min Range: -8.3107
Max Act: 8.0607. Min Act: -0.1700
Data Index: 167255 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.9982. Min Act: -0.1700
Data Index: 5501899 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.8107. Min Act: -0.1700
Data Index: 4508592 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.8107. Min Act: -0.1700
Data Index: 6560287 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.6857. Min Act: -0.1700
Data Index: 8557434 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.6857. Min Act: -0.1700
Data Index: 5401127 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.6857. Min Act: -0.1700
Data Index: 4616574 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.6545. Min Act: -0.1700
Data Index: 922356 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.6232. Min Act: -0.1700
Data Index: 245922 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.5607. Min Act: -0.1700
Data Index: 7897454 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.5295. Min Act: -0.1700
Data Index: 8366014 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.4982. Min Act: -0.1700
Data Index: 2494683 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.4670. Min Act: -0.1700
Data Index: 7936263 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.4982. Min Act: -0.1700
Data Index: 2171190 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.4670. Min Act: -0.1700
Data Index: 3585634 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3107. Min Range: -8.3107
Max Act: 7.4357. Min Act: -0.1700
Data Index: 813146 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19