Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 357 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.8766. Min Act: -0.1700
Data Index: 5795161 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.8141. Min Act: -0.1700
Data Index: 34157 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.5954. Min Act: -0.1700
Data Index: 6826673 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.4391. Min Act: -0.1700
Data Index: 4030190 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.1266. Min Act: -0.1700
Data Index: 7318246 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.1266. Min Act: -0.1700
Data Index: 368834 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.1266. Min Act: -0.1700
Data Index: 7788057 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.0954. Min Act: -0.1700
Data Index: 6809875 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.0329. Min Act: -0.1700
Data Index: 7698791 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.0016. Min Act: -0.1700
Data Index: 7943674 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.0016. Min Act: -0.1700
Data Index: 2987725 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8766. Min Range: -7.8766
Max Act: 7.0016. Min Act: -0.1700
Data Index: 6479490 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8766. Min Range: -7.8766
Max Act: 6.9391. Min Act: -0.1700
Data Index: 4692019 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8766. Min Range: -7.8766
Max Act: 6.8766. Min Act: -0.1700
Data Index: 4692016 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8766. Min Range: -7.8766
Max Act: 6.8766. Min Act: -0.1700
Data Index: 2428946 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8766. Min Range: -7.8766
Max Act: 6.8766. Min Act: -0.1700
Data Index: 1355136 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8766. Min Range: -7.8766
Max Act: 6.8766. Min Act: -0.1700
Data Index: 7944082 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8766. Min Range: -7.8766
Max Act: 6.8766. Min Act: -0.1700
Data Index: 6970426 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8766. Min Range: -7.8766
Max Act: 6.8454. Min Act: -0.1700
Data Index: 2274465 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8766. Min Range: -7.8766
Max Act: 6.8454. Min Act: -0.1700
Data Index: 826861 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19