Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5031 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0815. Min Range: -8.0815
Max Act: 8.0815. Min Act: -0.1700
Data Index: 5766759 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.9252. Min Act: -0.1700
Data Index: 2748369 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.7065. Min Act: -0.1700
Data Index: 7187849 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.4877. Min Act: -0.1700
Data Index: 3677681 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.4877. Min Act: -0.1700
Data Index: 108577 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.4565. Min Act: -0.1700
Data Index: 6745544 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.4252. Min Act: -0.1700
Data Index: 5842501 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.4252. Min Act: -0.1696
Data Index: 6051948 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.3940. Min Act: -0.1700
Data Index: 3617459 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.3940. Min Act: -0.1700
Data Index: 5725627 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.3315. Min Act: -0.1700
Data Index: 7612891 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.3315. Min Act: -0.1700
Data Index: 3114569 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.3315. Min Act: -0.1700
Data Index: 2194149 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.3315. Min Act: -0.1700
Data Index: 3009339 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.3002. Min Act: -0.1700
Data Index: 3374581 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.2690. Min Act: -0.1700
Data Index: 5199706 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.2690. Min Act: -0.1700
Data Index: 6883049 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.2377. Min Act: -0.1700
Data Index: 3872257 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.2690. Min Act: -0.1700
Data Index: 838289 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0815. Min Range: -8.0815
Max Act: 7.3002. Min Act: -0.1700
Data Index: 1261819 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19