Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2200 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.5934. Min Act: -0.1700
Data Index: 3373422 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.5309. Min Act: -0.1700
Data Index: 8624738 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.4996. Min Act: -0.1700
Data Index: 3373420 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.4059. Min Act: -0.1700
Data Index: 3901534 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.3121. Min Act: -0.1700
Data Index: 8745075 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.2809. Min Act: -0.1700
Data Index: 5826644 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.2496. Min Act: -0.1700
Data Index: 3946507 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.2496. Min Act: -0.1700
Data Index: 427856 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.2184. Min Act: -0.1700
Data Index: 6391813 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.2184. Min Act: -0.1700
Data Index: 8820443 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.1871. Min Act: -0.1700
Data Index: 8418463 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.1871. Min Act: -0.1700
Data Index: 5961732 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.1559. Min Act: -0.1700
Data Index: 5970166 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.1246. Min Act: -0.1700
Data Index: 6733131 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.1246. Min Act: -0.1700
Data Index: 6169318 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.1246. Min Act: -0.1700
Data Index: 5691373 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.1246. Min Act: -0.1700
Data Index: 7497858 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.0934. Min Act: -0.1700
Data Index: 8177018 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.0934. Min Act: -0.1700
Data Index: 6519732 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5934. Min Range: -5.5934
Max Act: 5.0934. Min Act: -0.1700
Data Index: 7310890 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19