Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.7093. Min Act: -0.1700
Data Index: 1637819 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.6468. Min Act: -0.1700
Data Index: 5165235 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.5218. Min Act: -0.1700
Data Index: 8672314 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.3343. Min Act: -0.1700
Data Index: 4314079 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.3968. Min Act: -0.1700
Data Index: 4092971 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.3343. Min Act: -0.1700
Data Index: 8368186 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.2718. Min Act: -0.1700
Data Index: 1225672 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.3343. Min Act: -0.1700
Data Index: 2039289 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.1468. Min Act: -0.1700
Data Index: 128010 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.1468. Min Act: -0.1700
Data Index: 6723321 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.2093. Min Act: -0.1700
Data Index: 6075637 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.1468. Min Act: -0.1700
Data Index: 4354521 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.1468. Min Act: -0.1700
Data Index: 4796489 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.0843. Min Act: -0.1700
Data Index: 6910529 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.0843. Min Act: -0.1700
Data Index: 3587612 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.0843. Min Act: -0.1700
Data Index: 1883936 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.0843. Min Act: -0.1700
Data Index: 2393351 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.0218. Min Act: -0.1700
Data Index: 3488546 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7093. Min Range: -8.7093
Max Act: 8.0218. Min Act: -0.1700
Data Index: 2535597 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7093. Min Range: -8.7093
Max Act: 7.9593. Min Act: -0.1700
Data Index: 2040399 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19