Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 748 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.7244. Min Act: -0.1700
Data Index: 2560480 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.6306. Min Act: -0.1700
Data Index: 5405943 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.5681. Min Act: -0.1700
Data Index: 5002592 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.5681. Min Act: -0.1700
Data Index: 6920842 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.5056. Min Act: -0.1700
Data Index: 1638523 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.4744. Min Act: -0.1700
Data Index: 6688958 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.4431. Min Act: -0.1700
Data Index: 1017377 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.4431. Min Act: -0.1700
Data Index: 1761346 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.4431. Min Act: -0.1700
Data Index: 2362959 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3806. Min Act: -0.1700
Data Index: 604165 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3806. Min Act: -0.1700
Data Index: 8629946 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3806. Min Act: -0.1700
Data Index: 6241029 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3494. Min Act: -0.1700
Data Index: 1001694 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3806. Min Act: -0.1700
Data Index: 7766401 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3494. Min Act: -0.1700
Data Index: 7507097 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3181. Min Act: -0.1700
Data Index: 2459630 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3181. Min Act: -0.1700
Data Index: 5875849 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3181. Min Act: -0.1700
Data Index: 4372059 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3181. Min Act: -0.1700
Data Index: 6799767 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7244. Min Range: -5.7244
Max Act: 5.3181. Min Act: -0.1700
Data Index: 261144 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19