Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2140 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4574. Min Range: -6.4574
Max Act: 6.4574. Min Act: -0.1700
Data Index: 3343046 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4574. Min Range: -6.4574
Max Act: 6.3636. Min Act: -0.1700
Data Index: 3045152 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4574. Min Range: -6.4574
Max Act: 6.2074. Min Act: -0.1700
Data Index: 3543821 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4574. Min Range: -6.4574
Max Act: 6.0511. Min Act: -0.1700
Data Index: 3479089 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4574. Min Range: -6.4574
Max Act: 6.0511. Min Act: -0.1700
Data Index: 1112022 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4574. Min Range: -6.4574
Max Act: 6.0511. Min Act: -0.1700
Data Index: 7936029 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.9886. Min Act: -0.1700
Data Index: 3346854 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.9574. Min Act: -0.1700
Data Index: 1902054 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.8949. Min Act: -0.1700
Data Index: 288835 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.8636. Min Act: -0.1700
Data Index: 2973526 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.8324. Min Act: -0.1700
Data Index: 3525047 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.8011. Min Act: -0.1700
Data Index: 7671061 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.8324. Min Act: -0.1700
Data Index: 1751187 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.8324. Min Act: -0.1700
Data Index: 254213 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.8011. Min Act: -0.1700
Data Index: 3861957 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.8011. Min Act: -0.1700
Data Index: 2284153 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.7699. Min Act: -0.1700
Data Index: 6610965 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.7699. Min Act: -0.1700
Data Index: 7429739 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.7699. Min Act: -0.1700
Data Index: 4530589 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4574. Min Range: -6.4574
Max Act: 5.7074. Min Act: -0.1700
Data Index: 8587643 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19