Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 657 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.9551. Min Act: -0.1700
Data Index: 7434444 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8759. Min Act: -0.1700
Data Index: 4548372 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8600. Min Act: -0.1700
Data Index: 1697748 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8759. Min Act: -0.1700
Data Index: 917895 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8441. Min Act: -0.1700
Data Index: 4982505 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8282. Min Act: -0.1700
Data Index: 3921702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8123. Min Act: -0.1700
Data Index: 5099500 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8123. Min Act: -0.1700
Data Index: 3253632 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8123. Min Act: -0.1700
Data Index: 5259653 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8123. Min Act: -0.1700
Data Index: 3186573 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.8123. Min Act: -0.1700
Data Index: 3050455 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.7964. Min Act: -0.1700
Data Index: 1335547 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.7964. Min Act: -0.1700
Data Index: 4129182 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.7964. Min Act: -0.1700
Data Index: 4113704 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.7964. Min Act: -0.1700
Data Index: 8006060 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.7964. Min Act: -0.1700
Data Index: 7483437 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.7964. Min Act: -0.1700
Data Index: 2129384 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.7805. Min Act: -0.1700
Data Index: 2674725 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.7805. Min Act: -0.1700
Data Index: 4299742 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9551. Min Range: -2.9551
Max Act: 2.7805. Min Act: -0.1700
Data Index: 3414668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19