Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.8168. Min Act: -0.1700
Data Index: 4335161 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.7543. Min Act: -0.1700
Data Index: 7260089 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.5980. Min Act: -0.1700
Data Index: 3447349 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.5980. Min Act: -0.1700
Data Index: 3447350 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.5668. Min Act: -0.1700
Data Index: 4703694 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.5668. Min Act: -0.1700
Data Index: 4886114 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.5668. Min Act: -0.1700
Data Index: 2502714 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.5355. Min Act: -0.1700
Data Index: 6847574 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.5043. Min Act: -0.1700
Data Index: 5640422 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.4418. Min Act: -0.1700
Data Index: 4258646 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.3793. Min Act: -0.1700
Data Index: 5488920 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.3793. Min Act: -0.1700
Data Index: 4374018 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.3168. Min Act: -0.1700
Data Index: 4611315 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.3168. Min Act: -0.1700
Data Index: 7506381 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.2855. Min Act: -0.1700
Data Index: 5313619 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.2855. Min Act: -0.1700
Data Index: 3697650 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.2855. Min Act: -0.1700
Data Index: 955283 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.2543. Min Act: -0.1700
Data Index: 6155634 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.2543. Min Act: -0.1700
Data Index: 6359199 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8168. Min Range: -6.8168
Max Act: 6.2543. Min Act: -0.1700
Data Index: 7256389 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19