Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.5470. Min Act: -0.1700
Data Index: 8618286 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.3595. Min Act: -0.1700
Data Index: 851260 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.3283. Min Act: -0.1700
Data Index: 852993 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.3283. Min Act: -0.1700
Data Index: 2632913 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.3283. Min Act: -0.1700
Data Index: 4089148 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.3283. Min Act: -0.1700
Data Index: 7284580 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2970. Min Act: -0.1700
Data Index: 6841888 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2970. Min Act: -0.1700
Data Index: 5650764 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2970. Min Act: -0.1700
Data Index: 3603201 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2970. Min Act: -0.1700
Data Index: 5233491 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2970. Min Act: -0.1700
Data Index: 7038061 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2345. Min Act: -0.1700
Data Index: 3394197 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2658. Min Act: -0.1700
Data Index: 6245164 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2970. Min Act: -0.1700
Data Index: 6591596 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2658. Min Act: -0.1700
Data Index: 5728847 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2658. Min Act: -0.1700
Data Index: 1647251 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2658. Min Act: -0.1700
Data Index: 2798530 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2345. Min Act: -0.1700
Data Index: 7570622 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2345. Min Act: -0.1700
Data Index: 7850062 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5470. Min Range: -7.5470
Max Act: 7.2345. Min Act: -0.1700
Data Index: 831359 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19