Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3048 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5819. Min Range: -7.5819
Max Act: 7.5819. Min Act: -0.1700
Data Index: 7125517 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5819. Min Range: -7.5819
Max Act: 7.4569. Min Act: -0.1700
Data Index: 2949484 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5819. Min Range: -7.5819
Max Act: 7.3944. Min Act: -0.1700
Data Index: 8311137 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5819. Min Range: -7.5819
Max Act: 7.3632. Min Act: -0.1700
Data Index: 2423944 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5819. Min Range: -7.5819
Max Act: 7.2694. Min Act: -0.1700
Data Index: 2149759 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5819. Min Range: -7.5819
Max Act: 7.2069. Min Act: -0.1700
Data Index: 2268583 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5819. Min Range: -7.5819
Max Act: 7.0507. Min Act: -0.1700
Data Index: 4118491 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.9569. Min Act: -0.1700
Data Index: 4035167 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.9257. Min Act: -0.1700
Data Index: 1105271 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.9257. Min Act: -0.1700
Data Index: 3555485 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.8632. Min Act: -0.1700
Data Index: 7352958 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.8632. Min Act: -0.1700
Data Index: 8137916 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.8319. Min Act: -0.1700
Data Index: 1739397 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.8319. Min Act: -0.1700
Data Index: 7383435 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.8007. Min Act: -0.1700
Data Index: 4529525 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.8319. Min Act: -0.1700
Data Index: 5837900 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.7694. Min Act: -0.1700
Data Index: 2665607 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.7694. Min Act: -0.1700
Data Index: 6486927 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.6757. Min Act: -0.1700
Data Index: 7383436 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5819. Min Range: -7.5819
Max Act: 6.7069. Min Act: -0.1700
Data Index: 2590632 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19