Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0043. Min Range: -6.0043
Max Act: 6.0043. Min Act: -0.1700
Data Index: 7814737 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.7543. Min Act: -0.1700
Data Index: 5998836 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.7543. Min Act: -0.1700
Data Index: 305141 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.6918. Min Act: -0.1700
Data Index: 7869838 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.6605. Min Act: -0.1700
Data Index: 4521552 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.6293. Min Act: -0.1700
Data Index: 2353809 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5980. Min Act: -0.1700
Data Index: 2500274 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5980. Min Act: -0.1700
Data Index: 3701395 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5980. Min Act: -0.1700
Data Index: 2716177 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5980. Min Act: -0.1700
Data Index: 7697945 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5668. Min Act: -0.1700
Data Index: 4938253 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5668. Min Act: -0.1700
Data Index: 2659557 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5668. Min Act: -0.1700
Data Index: 6781957 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5668. Min Act: -0.1700
Data Index: 4716840 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5355. Min Act: -0.1700
Data Index: 3417930 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5355. Min Act: -0.1700
Data Index: 7745107 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5355. Min Act: -0.1700
Data Index: 5730259 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5668. Min Act: -0.1700
Data Index: 7832378 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5355. Min Act: -0.1700
Data Index: 3149203 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0043. Min Range: -6.0043
Max Act: 5.5355. Min Act: -0.1700
Data Index: 6711430 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19