Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 591 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0133. Min Range: -7.0133
Max Act: 7.0133. Min Act: -0.1700
Data Index: 7550213 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.9820. Min Act: -0.1700
Data Index: 8809274 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.9195. Min Act: -0.1700
Data Index: 5111238 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.8883. Min Act: -0.1700
Data Index: 716511 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.8883. Min Act: -0.1700
Data Index: 7674252 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.8570. Min Act: -0.1700
Data Index: 4097734 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.8570. Min Act: -0.1700
Data Index: 3864611 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.7945. Min Act: -0.1700
Data Index: 5884813 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.7945. Min Act: -0.1700
Data Index: 3619249 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.7945. Min Act: -0.1700
Data Index: 2791619 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.7008. Min Act: -0.1700
Data Index: 8302814 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.7320. Min Act: -0.1700
Data Index: 2696040 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.7008. Min Act: -0.1700
Data Index: 3908139 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.6695. Min Act: -0.1700
Data Index: 5779548 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.6695. Min Act: -0.1700
Data Index: 7951249 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.6695. Min Act: -0.1700
Data Index: 124420 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.6383. Min Act: -0.1700
Data Index: 7733940 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.6383. Min Act: -0.1700
Data Index: 8068520 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.6070. Min Act: -0.1700
Data Index: 3404466 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0133. Min Range: -7.0133
Max Act: 6.6070. Min Act: -0.1700
Data Index: 7378346 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19