Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.3515. Min Act: -0.1700
Data Index: 8718661 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.2890. Min Act: -0.1700
Data Index: 5831278 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1952. Min Act: -0.1700
Data Index: 385789 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1640. Min Act: -0.1700
Data Index: 4026583 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 1993481 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0702. Min Act: -0.1700
Data Index: 615403 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 7908352 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 711197 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 8276634 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0702. Min Act: -0.1700
Data Index: 1042106 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0077. Min Act: -0.1700
Data Index: 1203962 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0077. Min Act: -0.1700
Data Index: 1987492 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 4128088 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0077. Min Act: -0.1700
Data Index: 2610003 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0077. Min Act: -0.1700
Data Index: 8593075 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 741448 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9140. Min Act: -0.1700
Data Index: 8196274 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9452. Min Act: -0.1700
Data Index: 4580215 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9452. Min Act: -0.1700
Data Index: 410991 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9452. Min Act: -0.1700
Data Index: 8519687 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19