Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4354 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.9029. Min Act: -0.1700
Data Index: 2240785 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.7154. Min Act: -0.1700
Data Index: 6727089 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.7154. Min Act: -0.1700
Data Index: 8405545 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.6529. Min Act: -0.1700
Data Index: 2541375 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.5904. Min Act: -0.1700
Data Index: 5819621 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.5592. Min Act: -0.1700
Data Index: 1303946 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.4967. Min Act: -0.1700
Data Index: 75188 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.4654. Min Act: -0.1700
Data Index: 4136182 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.4654. Min Act: -0.1700
Data Index: 7642023 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.4654. Min Act: -0.1700
Data Index: 747898 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.4029. Min Act: -0.1700
Data Index: 2674053 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.4029. Min Act: -0.1700
Data Index: 2202112 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.3404. Min Act: -0.1700
Data Index: 3349999 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.3404. Min Act: -0.1700
Data Index: 734096 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.3092. Min Act: -0.1700
Data Index: 4743261 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.3092. Min Act: -0.1700
Data Index: 4593323 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.2779. Min Act: -0.1700
Data Index: 6029797 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.2779. Min Act: -0.1700
Data Index: 4067412 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.2467. Min Act: -0.1700
Data Index: 633733 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9029. Min Range: -5.9029
Max Act: 5.2467. Min Act: -0.1700
Data Index: 5419614 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19