Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.3404. Min Act: -0.1700
Data Index: 3099809 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.2467. Min Act: -0.1700
Data Index: 6839499 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.2467. Min Act: -0.1700
Data Index: 7811732 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.2467. Min Act: -0.1700
Data Index: 5109706 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.2154. Min Act: -0.1700
Data Index: 5324354 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.2154. Min Act: -0.1700
Data Index: 5526049 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.2154. Min Act: -0.1700
Data Index: 7104584 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1842. Min Act: -0.1700
Data Index: 8486211 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1842. Min Act: -0.1700
Data Index: 1516247 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1529. Min Act: -0.1700
Data Index: 7279500 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1529. Min Act: -0.1700
Data Index: 410355 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1529. Min Act: -0.1700
Data Index: 7974144 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1529. Min Act: -0.1700
Data Index: 8038435 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1529. Min Act: -0.1700
Data Index: 8056464 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1529. Min Act: -0.1700
Data Index: 3409957 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1217. Min Act: -0.1700
Data Index: 644507 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1529. Min Act: -0.1700
Data Index: 1381768 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.0904. Min Act: -0.1700
Data Index: 68022 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.1217. Min Act: -0.1700
Data Index: 4543567 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.0904. Min Act: -0.1700
Data Index: 282976 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19