Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.8983. Min Act: -0.1700
Data Index: 1407205 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.3670. Min Act: -0.1700
Data Index: 4266210 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.3670. Min Act: -0.1700
Data Index: 6503888 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.3358. Min Act: -0.1700
Data Index: 3625227 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.2420. Min Act: -0.1700
Data Index: 5446940 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.2420. Min Act: -0.1700
Data Index: 3308947 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.2420. Min Act: -0.1700
Data Index: 1811445 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.2108. Min Act: -0.1700
Data Index: 4956370 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.1795. Min Act: -0.1700
Data Index: 5991195 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.2108. Min Act: -0.1700
Data Index: 3920383 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.1483. Min Act: -0.1700
Data Index: 8326010 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.1170. Min Act: -0.1700
Data Index: 3346470 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.1170. Min Act: -0.1700
Data Index: 4571486 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.0858. Min Act: -0.1700
Data Index: 1506551 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.0545. Min Act: -0.1700
Data Index: 6106342 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.0858. Min Act: -0.1700
Data Index: 6556641 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.0545. Min Act: -0.1700
Data Index: 95977 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.0233. Min Act: -0.1700
Data Index: 4031995 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.0233. Min Act: -0.1700
Data Index: 6045442 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8983. Min Range: -7.8983
Max Act: 7.0233. Min Act: -0.1700
Data Index: 7822422 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19