Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6418. Min Range: -5.6418
Max Act: 5.6418. Min Act: -0.1700
Data Index: 507102 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6418. Min Range: -5.6418
Max Act: 5.1730. Min Act: -0.1700
Data Index: 4934966 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6418. Min Range: -5.6418
Max Act: 5.1105. Min Act: -0.1700
Data Index: 3036174 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6418. Min Range: -5.6418
Max Act: 5.0168. Min Act: -0.1700
Data Index: 3327186 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.9855. Min Act: -0.1700
Data Index: 2042290 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.9543. Min Act: -0.1700
Data Index: 231944 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.9543. Min Act: -0.1700
Data Index: 8117019 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.9543. Min Act: -0.1700
Data Index: 8730253 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.9230. Min Act: -0.1700
Data Index: 2544103 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.9543. Min Act: -0.1700
Data Index: 341316 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.9543. Min Act: -0.1700
Data Index: 7257364 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.8918. Min Act: -0.1700
Data Index: 6307440 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.8605. Min Act: -0.1700
Data Index: 1221093 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.8605. Min Act: -0.1700
Data Index: 2293697 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.8605. Min Act: -0.1700
Data Index: 3534592 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.8605. Min Act: -0.1700
Data Index: 5884788 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.8605. Min Act: -0.1700
Data Index: 7373890 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.8918. Min Act: -0.1700
Data Index: 678359 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.8293. Min Act: -0.1700
Data Index: 3067552 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6418. Min Range: -5.6418
Max Act: 4.8293. Min Act: -0.1700
Data Index: 480308 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19