Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3439 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.9049. Min Act: -0.1700
Data Index: 1331175 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.8112. Min Act: -0.1700
Data Index: 5823344 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.8424. Min Act: -0.1700
Data Index: 3288745 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.7799. Min Act: -0.1700
Data Index: 91509 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.7174. Min Act: -0.1700
Data Index: 3916090 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.7487. Min Act: -0.1700
Data Index: 488421 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.7487. Min Act: -0.1700
Data Index: 2716519 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.7174. Min Act: -0.1700
Data Index: 3162274 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.7174. Min Act: -0.1700
Data Index: 2299395 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.7174. Min Act: -0.1700
Data Index: 4644677 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6862. Min Act: -0.1700
Data Index: 833516 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6549. Min Act: -0.1700
Data Index: 8030415 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6862. Min Act: -0.1700
Data Index: 5445822 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6549. Min Act: -0.1700
Data Index: 6995324 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6549. Min Act: -0.1700
Data Index: 4919714 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6549. Min Act: -0.1700
Data Index: 2830206 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6237. Min Act: -0.1700
Data Index: 4002131 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6549. Min Act: -0.1700
Data Index: 7676550 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6862. Min Act: -0.1700
Data Index: 6962068 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9049. Min Range: -4.9049
Max Act: 4.6549. Min Act: -0.1700
Data Index: 926570 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19