Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4474 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.8409. Min Act: -0.1700
Data Index: 6704075 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.7471. Min Act: -0.1700
Data Index: 8297650 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.7159. Min Act: -0.1700
Data Index: 3069792 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.6846. Min Act: -0.1700
Data Index: 6704071 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.6534. Min Act: -0.1700
Data Index: 699169 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.5909. Min Act: -0.1700
Data Index: 3802931 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.5909. Min Act: -0.1700
Data Index: 789717 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.5596. Min Act: -0.1700
Data Index: 6209627 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.5284. Min Act: -0.1700
Data Index: 2545996 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.4971. Min Act: -0.1700
Data Index: 3328750 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.3721. Min Act: -0.1700
Data Index: 4869186 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.3721. Min Act: -0.1700
Data Index: 3529420 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.3721. Min Act: -0.1700
Data Index: 1567084 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.3721. Min Act: -0.1700
Data Index: 368765 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.3721. Min Act: -0.1700
Data Index: 3071516 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.3096. Min Act: -0.1700
Data Index: 723858 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.3409. Min Act: -0.1700
Data Index: 787832 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.3096. Min Act: -0.1700
Data Index: 4496225 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.3096. Min Act: -0.1700
Data Index: 1502911 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8409. Min Range: -6.8409
Max Act: 6.2784. Min Act: -0.1700
Data Index: 7396380 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19