Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.6339. Min Act: -0.1700
Data Index: 7939700 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.6652. Min Act: -0.1700
Data Index: 8716150 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.6339. Min Act: -0.1700
Data Index: 8218260 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.5402. Min Act: -0.1700
Data Index: 3634107 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.4777. Min Act: -0.1700
Data Index: 5727715 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.5089. Min Act: -0.1700
Data Index: 5077534 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.4777. Min Act: -0.1700
Data Index: 6062672 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.4464. Min Act: -0.1700
Data Index: 397621 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.4464. Min Act: -0.1700
Data Index: 3072890 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.4464. Min Act: -0.1700
Data Index: 535409 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.4152. Min Act: -0.1700
Data Index: 4300745 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.4464. Min Act: -0.1700
Data Index: 2328050 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.4464. Min Act: -0.1700
Data Index: 8174581 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3839. Min Act: -0.1700
Data Index: 6028523 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3527. Min Act: -0.1700
Data Index: 3292922 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3214. Min Act: -0.1700
Data Index: 4122662 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3214. Min Act: -0.1700
Data Index: 7154298 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3214. Min Act: -0.1700
Data Index: 2278387 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3214. Min Act: -0.1700
Data Index: 2574848 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3214. Min Act: -0.1700
Data Index: 7958950 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19