Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.9682. Min Act: -0.1700
Data Index: 793091 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.8745. Min Act: -0.1700
Data Index: 7527587 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.8745. Min Act: -0.1700
Data Index: 8297627 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.8432. Min Act: -0.1700
Data Index: 2834342 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.6870. Min Act: -0.1700
Data Index: 1614330 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.6870. Min Act: -0.1700
Data Index: 841275 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.6870. Min Act: -0.1700
Data Index: 6581535 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.6557. Min Act: -0.1700
Data Index: 1886754 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.6870. Min Act: -0.1700
Data Index: 266668 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.6245. Min Act: -0.1700
Data Index: 3393394 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.6245. Min Act: -0.1700
Data Index: 1503045 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.6245. Min Act: -0.1700
Data Index: 2740866 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.5932. Min Act: -0.1700
Data Index: 2143315 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.5620. Min Act: -0.1700
Data Index: 667456 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.5620. Min Act: -0.1700
Data Index: 8134403 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.5620. Min Act: -0.1700
Data Index: 5403401 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.5620. Min Act: -0.1700
Data Index: 8686211 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.5932. Min Act: -0.1700
Data Index: 6572587 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.5620. Min Act: -0.1700
Data Index: 3081350 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9682. Min Range: -6.9682
Max Act: 6.5307. Min Act: -0.1700
Data Index: 2582096 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19