Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0677. Min Range: -5.0677
Max Act: 5.0677. Min Act: -0.1700
Data Index: 4619087 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0677. Min Range: -5.0677
Max Act: 5.0677. Min Act: -0.1700
Data Index: 8794925 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0677. Min Range: -5.0677
Max Act: 5.0052. Min Act: -0.1700
Data Index: 1539864 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0677. Min Range: -5.0677
Max Act: 5.0052. Min Act: -0.1700
Data Index: 2938059 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.9427. Min Act: -0.1700
Data Index: 2000802 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.9114. Min Act: -0.1700
Data Index: 8367946 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.9114. Min Act: -0.1700
Data Index: 3031757 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.9114. Min Act: -0.1700
Data Index: 7602971 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.8489. Min Act: -0.1700
Data Index: 5918320 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.8489. Min Act: -0.1700
Data Index: 3123749 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.8489. Min Act: -0.1700
Data Index: 874543 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.8177. Min Act: -0.1700
Data Index: 3256732 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.8177. Min Act: -0.1700
Data Index: 2101294 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.7864. Min Act: -0.1700
Data Index: 2774119 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.7864. Min Act: -0.1700
Data Index: 1404904 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.7864. Min Act: -0.1700
Data Index: 770431 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.7552. Min Act: -0.1700
Data Index: 2909440 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.7552. Min Act: -0.1700
Data Index: 1833523 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.7552. Min Act: -0.1700
Data Index: 8003808 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0677. Min Range: -5.0677
Max Act: 4.7239. Min Act: -0.1700
Data Index: 4808689 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19