Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2161 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.9480. Min Act: -0.1700
Data Index: 992943 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.8543. Min Act: -0.1700
Data Index: 2824538 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.7918. Min Act: -0.1700
Data Index: 6373547 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.6980. Min Act: -0.1700
Data Index: 2618593 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.6980. Min Act: -0.1700
Data Index: 6913664 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.6043. Min Act: -0.1700
Data Index: 5265433 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.5730. Min Act: -0.1700
Data Index: 2148267 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.4793. Min Act: -0.1700
Data Index: 906701 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.4168. Min Act: -0.1700
Data Index: 1554420 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.3543. Min Act: -0.1700
Data Index: 2496966 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.3230. Min Act: -0.1700
Data Index: 316955 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.2918. Min Act: -0.1700
Data Index: 8354874 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.2918. Min Act: -0.1700
Data Index: 3614595 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.3230. Min Act: -0.1700
Data Index: 812111 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.2918. Min Act: -0.1700
Data Index: 3770554 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.2605. Min Act: -0.1700
Data Index: 4018744 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.2605. Min Act: -0.1700
Data Index: 1216607 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.2293. Min Act: -0.1700
Data Index: 5798227 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.1980. Min Act: -0.1700
Data Index: 1440999 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9480. Min Range: -6.9480
Max Act: 6.2293. Min Act: -0.1700
Data Index: 7798951 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19