Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.5202. Min Act: -0.1700
Data Index: 5047624 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2077. Min Act: -0.1700
Data Index: 1347657 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.1764. Min Act: -0.1700
Data Index: 697818 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.1764. Min Act: -0.1700
Data Index: 4029870 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.1764. Min Act: -0.1700
Data Index: 1258678 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.1452. Min Act: -0.1700
Data Index: 8094675 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.1139. Min Act: -0.1700
Data Index: 2872924 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.0827. Min Act: -0.1700
Data Index: 5964892 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.0827. Min Act: -0.1700
Data Index: 6409654 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.0202. Min Act: -0.1700
Data Index: 3269584 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.0202. Min Act: -0.1700
Data Index: 5155189 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.0202. Min Act: -0.1700
Data Index: 290507 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5202. Min Range: -5.5202
Max Act: 4.9889. Min Act: -0.1700
Data Index: 4829733 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5202. Min Range: -5.5202
Max Act: 4.9889. Min Act: -0.1700
Data Index: 693128 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5202. Min Range: -5.5202
Max Act: 4.9577. Min Act: -0.1700
Data Index: 600949 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5202. Min Range: -5.5202
Max Act: 4.9577. Min Act: -0.1700
Data Index: 1349895 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5202. Min Range: -5.5202
Max Act: 4.9264. Min Act: -0.1700
Data Index: 4582939 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5202. Min Range: -5.5202
Max Act: 4.8952. Min Act: -0.1700
Data Index: 6869265 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5202. Min Range: -5.5202
Max Act: 4.9264. Min Act: -0.1700
Data Index: 4700622 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5202. Min Range: -5.5202
Max Act: 4.9264. Min Act: -0.1700
Data Index: 3590956 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19