Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2232 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2535. Min Range: -7.2535
Max Act: 7.2535. Min Act: -0.1700
Data Index: 7870842 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2535. Min Range: -7.2535
Max Act: 7.1285. Min Act: -0.1700
Data Index: 1299921 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2535. Min Range: -7.2535
Max Act: 7.0972. Min Act: -0.1700
Data Index: 5895000 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2535. Min Range: -7.2535
Max Act: 7.0660. Min Act: -0.1700
Data Index: 7426379 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2535. Min Range: -7.2535
Max Act: 7.0347. Min Act: -0.1700
Data Index: 2486203 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2535. Min Range: -7.2535
Max Act: 7.0347. Min Act: -0.1700
Data Index: 4300054 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.9410. Min Act: -0.1700
Data Index: 2583762 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.9097. Min Act: -0.1700
Data Index: 5353015 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.9097. Min Act: -0.1700
Data Index: 5095458 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.9097. Min Act: -0.1700
Data Index: 6578809 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.8785. Min Act: -0.1700
Data Index: 8374806 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.8785. Min Act: -0.1700
Data Index: 7027182 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.8472. Min Act: -0.1700
Data Index: 6990621 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.8472. Min Act: -0.1700
Data Index: 2729022 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.7847. Min Act: -0.1700
Data Index: 4795826 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.7847. Min Act: -0.1700
Data Index: 139862 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.8160. Min Act: -0.1700
Data Index: 4573656 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.7847. Min Act: -0.1700
Data Index: 3694647 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.7535. Min Act: -0.1700
Data Index: 5277658 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2535. Min Range: -7.2535
Max Act: 6.7222. Min Act: -0.1700
Data Index: 4623614 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19