Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4424 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.3461. Min Act: -0.1700
Data Index: 6767689 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.2524. Min Act: -0.1700
Data Index: 935369 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.2211. Min Act: -0.1700
Data Index: 2375027 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.2211. Min Act: -0.1700
Data Index: 3622022 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.2211. Min Act: -0.1700
Data Index: 219273 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.1899. Min Act: -0.1700
Data Index: 5910377 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.1586. Min Act: -0.1700
Data Index: 5169429 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.1274. Min Act: -0.1700
Data Index: 6053672 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.1586. Min Act: -0.1700
Data Index: 6545815 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.0961. Min Act: -0.1700
Data Index: 8063741 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.0336. Min Act: -0.1700
Data Index: 467194 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.0336. Min Act: -0.1700
Data Index: 8551334 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.0336. Min Act: -0.1700
Data Index: 3404536 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.0649. Min Act: -0.1700
Data Index: 3311345 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.0024. Min Act: -0.1700
Data Index: 7617198 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.0024. Min Act: -0.1700
Data Index: 5732035 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3461. Min Range: -7.3461
Max Act: 7.0024. Min Act: -0.1700
Data Index: 2992070 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3461. Min Range: -7.3461
Max Act: 6.9711. Min Act: -0.1700
Data Index: 3504695 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3461. Min Range: -7.3461
Max Act: 6.9399. Min Act: -0.1700
Data Index: 6416951 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3461. Min Range: -7.3461
Max Act: 6.9711. Min Act: -0.1700
Data Index: 1131856 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19