Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2671 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.4364. Min Act: -0.1700
Data Index: 8072124 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.4364. Min Act: -0.1700
Data Index: 169931 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.4052. Min Act: -0.1700
Data Index: 4160354 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3739. Min Act: -0.1700
Data Index: 1396413 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3114. Min Act: -0.1700
Data Index: 3360008 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3427. Min Act: -0.1700
Data Index: 8713200 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3427. Min Act: -0.1700
Data Index: 1145706 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3427. Min Act: -0.1700
Data Index: 4063930 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3427. Min Act: -0.1700
Data Index: 2717392 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3427. Min Act: -0.1700
Data Index: 7473698 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3114. Min Act: -0.1700
Data Index: 5864364 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3114. Min Act: -0.1700
Data Index: 7799895 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3114. Min Act: -0.1700
Data Index: 5399534 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.3114. Min Act: -0.1700
Data Index: 4493534 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.2802. Min Act: -0.1700
Data Index: 7725126 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.2489. Min Act: -0.1700
Data Index: 951575 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.2802. Min Act: -0.1700
Data Index: 7535485 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.2802. Min Act: -0.1700
Data Index: 5708553 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.2802. Min Act: -0.1700
Data Index: 5708555 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4364. Min Range: -4.4364
Max Act: 4.2489. Min Act: -0.1700
Data Index: 226284 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19