Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 717 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.6416. Min Act: -0.1700
Data Index: 5215086 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.3291. Min Act: -0.1700
Data Index: 2768101 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.1415. Min Act: -0.1700
Data Index: 7681457 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0790. Min Act: -0.1700
Data Index: 7913143 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0790. Min Act: -0.1700
Data Index: 7635710 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0790. Min Act: -0.1700
Data Index: 305551 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 4028547 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 2095176 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 5095898 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 4167020 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 5878273 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 7854943 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 334675 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 4313693 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 8379110 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 6070123 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0478. Min Act: -0.1700
Data Index: 2092216 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0165. Min Act: -0.1700
Data Index: 2842510 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0165. Min Act: -0.1700
Data Index: 1344439 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6416. Min Range: -4.6416
Max Act: 4.0165. Min Act: -0.1700
Data Index: 5561750 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19