Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2670 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.3443. Min Act: -0.1700
Data Index: 8633166 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.0318. Min Act: -0.1700
Data Index: 8731384 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.0005. Min Act: -0.1700
Data Index: 6051329 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.9380. Min Act: -0.1700
Data Index: 2293784 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.8443. Min Act: -0.1700
Data Index: 3660865 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.8130. Min Act: -0.1700
Data Index: 5026042 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.7818. Min Act: -0.1700
Data Index: 1478911 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.7505. Min Act: -0.1700
Data Index: 1837039 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.8130. Min Act: -0.1700
Data Index: 3245112 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.7818. Min Act: -0.1700
Data Index: 717439 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.7505. Min Act: -0.1700
Data Index: 3697138 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.7505. Min Act: -0.1700
Data Index: 530538 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.6568. Min Act: -0.1700
Data Index: 5065226 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.6568. Min Act: -0.1700
Data Index: 1456615 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.5943. Min Act: -0.1700
Data Index: 8064401 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.5943. Min Act: -0.1700
Data Index: 200354 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.5630. Min Act: -0.1700
Data Index: 6021253 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.5318. Min Act: -0.1700
Data Index: 2455152 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.5005. Min Act: -0.1700
Data Index: 8365078 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.5005. Min Act: -0.1700
Data Index: 7003381 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19