Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0749. Min Act: -0.1700
Data Index: 299148 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9812. Min Act: -0.1700
Data Index: 3478761 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7937. Min Act: -0.1700
Data Index: 6640386 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.7624. Min Act: -0.1700
Data Index: 2942291 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6686. Min Act: -0.1700
Data Index: 3801172 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6061. Min Act: -0.1700
Data Index: 2413862 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6374. Min Act: -0.1700
Data Index: 5824250 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6374. Min Act: -0.1700
Data Index: 8074172 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6374. Min Act: -0.1700
Data Index: 6070830 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.6061. Min Act: -0.1700
Data Index: 3226413 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5749. Min Act: -0.1700
Data Index: 1148160 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5436. Min Act: -0.1700
Data Index: 7454879 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 4491086 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 3438725 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 7880276 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 4549891 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 219754 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 5840240 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.5124. Min Act: -0.1700
Data Index: 2866139 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.4811. Min Act: -0.1700
Data Index: 69660 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19