Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.6214. Min Act: -0.1700
Data Index: 270700 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.3089. Min Act: -0.1700
Data Index: 7914832 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.3089. Min Act: -0.1700
Data Index: 1098589 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.2464. Min Act: -0.1700
Data Index: 1662467 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.1526. Min Act: -0.1700
Data Index: 4525623 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.0901. Min Act: -0.1700
Data Index: 2152245 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.0276. Min Act: -0.1700
Data Index: 6897754 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.0589. Min Act: -0.1700
Data Index: 7911148 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.9651. Min Act: -0.1700
Data Index: 7491680 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.9651. Min Act: -0.1700
Data Index: 5763062 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.8714. Min Act: -0.1700
Data Index: 1460134 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.9026. Min Act: -0.1700
Data Index: 8121109 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.9026. Min Act: -0.1700
Data Index: 275112 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.9026. Min Act: -0.1700
Data Index: 809614 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.8714. Min Act: -0.1700
Data Index: 234889 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.8401. Min Act: -0.1700
Data Index: 7456020 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.8401. Min Act: -0.1700
Data Index: 524333 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.8714. Min Act: -0.1700
Data Index: 5576865 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.8401. Min Act: -0.1700
Data Index: 913986 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6214. Min Range: -6.6214
Max Act: 5.8401. Min Act: -0.1700
Data Index: 5387921 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19