Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5000 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2487. Min Range: -6.2487
Max Act: 6.2487. Min Act: -0.1700
Data Index: 7481769 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2487. Min Range: -6.2487
Max Act: 6.0925. Min Act: -0.1700
Data Index: 5190169 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2487. Min Range: -6.2487
Max Act: 6.0300. Min Act: -0.1700
Data Index: 3594828 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9987. Min Act: -0.1700
Data Index: 8075645 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9987. Min Act: -0.1700
Data Index: 1782730 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9987. Min Act: -0.1700
Data Index: 8550280 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9675. Min Act: -0.1700
Data Index: 4239115 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9675. Min Act: -0.1700
Data Index: 8134319 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9362. Min Act: -0.1700
Data Index: 5588186 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9987. Min Act: -0.1700
Data Index: 7727186 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9362. Min Act: -0.1700
Data Index: 926937 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9050. Min Act: -0.1700
Data Index: 8053563 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.8737. Min Act: -0.1700
Data Index: 3691674 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.9050. Min Act: -0.1700
Data Index: 3556540 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.8737. Min Act: -0.1700
Data Index: 2904961 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.8737. Min Act: -0.1700
Data Index: 1042652 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.8112. Min Act: -0.1700
Data Index: 1601364 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.8425. Min Act: -0.1700
Data Index: 6542339 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.8112. Min Act: -0.1700
Data Index: 3206017 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2487. Min Range: -6.2487
Max Act: 5.8112. Min Act: -0.1700
Data Index: 3041242 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19