Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2624 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.6169. Min Act: -0.1700
Data Index: 4947321 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.5686. Min Act: -0.1700
Data Index: 1393364 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.4227. Min Act: -0.1700
Data Index: 2941264 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.4064. Min Act: -0.1700
Data Index: 2108950 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.3737. Min Act: -0.1700
Data Index: 7534103 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.3574. Min Act: -0.1700
Data Index: 5251942 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.3246. Min Act: -0.1700
Data Index: 7989565 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.3081. Min Act: -0.1700
Data Index: 2057930 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2752. Min Act: -0.1700
Data Index: 2583149 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.3081. Min Act: -0.1700
Data Index: 816455 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2752. Min Act: -0.1700
Data Index: 5438804 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2752. Min Act: -0.1700
Data Index: 5897578 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2587. Min Act: -0.1700
Data Index: 4085237 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2752. Min Act: -0.1700
Data Index: 2963600 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2587. Min Act: -0.1700
Data Index: 1868972 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2752. Min Act: -0.1700
Data Index: 8450695 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2422. Min Act: -0.1700
Data Index: 3372104 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2587. Min Act: -0.1700
Data Index: 1163562 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2587. Min Act: -0.1700
Data Index: 4597201 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6169. Min Range: -2.6169
Max Act: 2.2587. Min Act: -0.1700
Data Index: 5358749 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19