Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6686. Min Range: -7.6686
Max Act: 7.6686. Min Act: -0.1700
Data Index: 6038094 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6686. Min Range: -7.6686
Max Act: 7.0748. Min Act: -0.1700
Data Index: 6253194 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.9498. Min Act: -0.1700
Data Index: 784433 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.9498. Min Act: -0.1700
Data Index: 1390837 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.9186. Min Act: -0.1700
Data Index: 6283487 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.9186. Min Act: -0.1700
Data Index: 3830637 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.9186. Min Act: -0.1700
Data Index: 1900140 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.9186. Min Act: -0.1700
Data Index: 2148933 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.9498. Min Act: -0.1700
Data Index: 6231273 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.8248. Min Act: -0.1700
Data Index: 2452358 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.7936. Min Act: -0.1700
Data Index: 3025057 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.8248. Min Act: -0.1700
Data Index: 2110774 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.7623. Min Act: -0.1700
Data Index: 1117112 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.7623. Min Act: -0.1700
Data Index: 2869722 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.7623. Min Act: -0.1700
Data Index: 2775877 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.7936. Min Act: -0.1700
Data Index: 4902167 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.7936. Min Act: -0.1700
Data Index: 8465192 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.7311. Min Act: -0.1700
Data Index: 4483998 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.7311. Min Act: -0.1700
Data Index: 5904429 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6686. Min Range: -7.6686
Max Act: 6.7311. Min Act: -0.1700
Data Index: 7703736 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19