Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 80 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.3651. Min Range: -9.3651
Max Act: 9.3651. Min Act: -0.1700
Data Index: 5565209 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3651. Min Range: -9.3651
Max Act: 9.0526. Min Act: -0.1700
Data Index: 8400606 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.9901. Min Act: -0.1700
Data Index: 4354780 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.9276. Min Act: -0.1700
Data Index: 5096306 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.9276. Min Act: -0.1700
Data Index: 624745 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.9276. Min Act: -0.1700
Data Index: 7911583 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.9276. Min Act: -0.1700
Data Index: 7767466 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.9901. Min Act: -0.1700
Data Index: 2151695 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.9901. Min Act: -0.1700
Data Index: 494233 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3651. Min Range: -9.3651
Max Act: 9.0526. Min Act: -0.1700
Data Index: 2915231 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.8651. Min Act: -0.1700
Data Index: 5013534 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.8651. Min Act: -0.1700
Data Index: 3980249 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.8651. Min Act: -0.1700
Data Index: 3444217 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.8651. Min Act: -0.1700
Data Index: 4062455 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.9276. Min Act: -0.1700
Data Index: 2976299 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.8026. Min Act: -0.1700
Data Index: 6944422 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.8026. Min Act: -0.1700
Data Index: 8665661 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.8651. Min Act: -0.1700
Data Index: 5575691 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.8026. Min Act: -0.1700
Data Index: 8125576 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3651. Min Range: -9.3651
Max Act: 8.8026. Min Act: -0.1700
Data Index: 7568654 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19