Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.9089. Min Act: -0.1700
Data Index: 6607423 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6276. Min Act: -0.1700
Data Index: 5244084 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5964. Min Act: -0.1700
Data Index: 4659914 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5964. Min Act: -0.1700
Data Index: 5055030 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5651. Min Act: -0.1700
Data Index: 5055029 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5651. Min Act: -0.1700
Data Index: 4659915 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5339. Min Act: -0.1700
Data Index: 6915989 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5339. Min Act: -0.1700
Data Index: 4623594 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5339. Min Act: -0.1700
Data Index: 2177475 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5026. Min Act: -0.1700
Data Index: 7366273 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5026. Min Act: -0.1700
Data Index: 3408169 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.4714. Min Act: -0.1700
Data Index: 8582245 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.4714. Min Act: -0.1700
Data Index: 6871221 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.4401. Min Act: -0.1700
Data Index: 4432582 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.4401. Min Act: -0.1700
Data Index: 3408170 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.4401. Min Act: -0.1700
Data Index: 4070779 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.4401. Min Act: -0.1700
Data Index: 231470 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.4089. Min Act: -0.1700
Data Index: 1470154 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.4089. Min Act: -0.1700
Data Index: 1532965 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.3776. Min Act: -0.1700
Data Index: 2605689 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19