Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5766 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1212. Min Range: -7.1212
Max Act: 7.1212. Min Act: -0.1700
Data Index: 4365316 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1212. Min Range: -7.1212
Max Act: 7.0587. Min Act: -0.1700
Data Index: 1270422 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.8712. Min Act: -0.1700
Data Index: 5665419 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.8087. Min Act: -0.1700
Data Index: 7367386 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.6525. Min Act: -0.1700
Data Index: 538218 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.6212. Min Act: -0.1700
Data Index: 3943268 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.6212. Min Act: -0.1700
Data Index: 1309779 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.3712. Min Act: -0.1700
Data Index: 3233028 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.3712. Min Act: -0.1700
Data Index: 6734993 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.3087. Min Act: -0.1700
Data Index: 7266085 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.2775. Min Act: -0.1700
Data Index: 681117 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.2775. Min Act: -0.1700
Data Index: 3478790 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.2462. Min Act: -0.1700
Data Index: 1378302 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.2462. Min Act: -0.1700
Data Index: 3154221 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.2462. Min Act: -0.1700
Data Index: 2805129 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.2150. Min Act: -0.1700
Data Index: 7218924 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.2150. Min Act: -0.1700
Data Index: 432031 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.1837. Min Act: -0.1700
Data Index: 6342990 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.1837. Min Act: -0.1700
Data Index: 2232860 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1212. Min Range: -7.1212
Max Act: 6.1525. Min Act: -0.1700
Data Index: 3740485 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19