Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.8143. Min Act: -0.1700
Data Index: 147225 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.8143. Min Act: -0.1700
Data Index: 2868978 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.7518. Min Act: -0.1700
Data Index: 8372534 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.7518. Min Act: -0.1700
Data Index: 4303548 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.7518. Min Act: -0.1700
Data Index: 4303550 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.7518. Min Act: -0.1700
Data Index: 6986865 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.6893. Min Act: -0.1700
Data Index: 3036458 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.6893. Min Act: -0.1700
Data Index: 2477666 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.6268. Min Act: -0.1700
Data Index: 6307919 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.5018. Min Act: -0.1700
Data Index: 2980555 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.5018. Min Act: -0.1700
Data Index: 7012837 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.5018. Min Act: -0.1700
Data Index: 405856 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.5018. Min Act: -0.1700
Data Index: 7012843 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.5018. Min Act: -0.1700
Data Index: 434289 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.4393. Min Act: -0.1700
Data Index: 3956031 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.3768. Min Act: -0.1700
Data Index: 6697564 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.4393. Min Act: -0.1700
Data Index: 8273297 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.4393. Min Act: -0.1700
Data Index: 5399375 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.5018. Min Act: -0.1700
Data Index: 5548383 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8143. Min Range: -8.8143
Max Act: 8.5018. Min Act: -0.1700
Data Index: 5559024 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19