Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2369 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.6707. Min Act: -0.1698
Data Index: 3896241 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.7020. Min Act: -0.1700
Data Index: 495541 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5770. Min Act: -0.1700
Data Index: 8069732 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5770. Min Act: -0.1700
Data Index: 8315462 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5770. Min Act: -0.1700
Data Index: 5462530 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5145. Min Act: -0.1700
Data Index: 980386 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5145. Min Act: -0.1700
Data Index: 2779117 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4832. Min Act: -0.1700
Data Index: 6350327 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4832. Min Act: -0.1697
Data Index: 5267518 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4207. Min Act: -0.1700
Data Index: 786179 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4207. Min Act: -0.1700
Data Index: 234825 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4520. Min Act: -0.1700
Data Index: 6936198 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4207. Min Act: -0.1700
Data Index: 3996372 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3895. Min Act: -0.1700
Data Index: 5075767 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3895. Min Act: -0.1700
Data Index: 6040055 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3895. Min Act: -0.1700
Data Index: 2491913 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3895. Min Act: -0.1700
Data Index: 6541678 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3895. Min Act: -0.1700
Data Index: 5611189 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4207. Min Act: -0.1700
Data Index: 2612075 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3582. Min Act: -0.1700
Data Index: 6063383 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19