Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 100 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.5894. Min Act: -0.1700
Data Index: 6159316 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.5894. Min Act: -0.1700
Data Index: 1654329 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.5269. Min Act: -0.1700
Data Index: 3023630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.5269. Min Act: -0.1700
Data Index: 885123 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.5269. Min Act: -0.1700
Data Index: 137879 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.5269. Min Act: -0.1700
Data Index: 954028 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.5269. Min Act: -0.1700
Data Index: 5848836 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.5269. Min Act: -0.1700
Data Index: 7055891 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4957. Min Act: -0.1699
Data Index: 132914 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4957. Min Act: -0.1699
Data Index: 1049184 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4957. Min Act: -0.1700
Data Index: 2284401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4957. Min Act: -0.1700
Data Index: 7256270 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4957. Min Act: -0.1700
Data Index: 454342 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4957. Min Act: -0.1700
Data Index: 3312129 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4957. Min Act: -0.1700
Data Index: 7341951 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4957. Min Act: -0.1700
Data Index: 4139870 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4644. Min Act: -0.1700
Data Index: 6902893 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4644. Min Act: -0.1700
Data Index: 2517832 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4644. Min Act: -0.1700
Data Index: 778175 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5894. Min Range: -4.5894
Max Act: 4.4644. Min Act: -0.1700
Data Index: 2701676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19