Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4321 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4817. Min Range: -7.4817
Max Act: 7.4817. Min Act: -0.1700
Data Index: 3153946 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4817. Min Range: -7.4817
Max Act: 7.3255. Min Act: -0.1700
Data Index: 6919200 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4817. Min Range: -7.4817
Max Act: 7.1380. Min Act: -0.1700
Data Index: 556083 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.9192. Min Act: -0.1700
Data Index: 741563 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.8567. Min Act: -0.1700
Data Index: 7274297 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.7942. Min Act: -0.1700
Data Index: 3768506 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.7942. Min Act: -0.1700
Data Index: 863728 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.7317. Min Act: -0.1700
Data Index: 11005 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.7005. Min Act: -0.1700
Data Index: 1201620 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.7005. Min Act: -0.1700
Data Index: 792020 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.7005. Min Act: -0.1700
Data Index: 6102710 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.7005. Min Act: -0.1700
Data Index: 7575776 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.7005. Min Act: -0.1700
Data Index: 1152472 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.6692. Min Act: -0.1700
Data Index: 1685436 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.6692. Min Act: -0.1700
Data Index: 3892174 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.6692. Min Act: -0.1700
Data Index: 6101510 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.6380. Min Act: -0.1700
Data Index: 1922355 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.6380. Min Act: -0.1700
Data Index: 5590674 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.6380. Min Act: -0.1700
Data Index: 7448440 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4817. Min Range: -7.4817
Max Act: 6.5755. Min Act: -0.1700
Data Index: 6065997 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19