Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5105 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.1934. Min Act: -0.1700
Data Index: 552897 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.1621. Min Act: -0.1700
Data Index: 4514404 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.1621. Min Act: -0.1700
Data Index: 4384481 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.1309. Min Act: -0.1700
Data Index: 3506047 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.0996. Min Act: -0.1700
Data Index: 161724 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.0371. Min Act: -0.1700
Data Index: 2614149 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.0371. Min Act: -0.1700
Data Index: 2718678 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.0059. Min Act: -0.1700
Data Index: 6295319 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.0059. Min Act: -0.1700
Data Index: 4495339 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9434. Min Act: -0.1700
Data Index: 4148044 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9121. Min Act: -0.1700
Data Index: 7097159 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9434. Min Act: -0.1700
Data Index: 3552297 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8809. Min Act: -0.1700
Data Index: 1485327 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9121. Min Act: -0.1700
Data Index: 1783173 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8809. Min Act: -0.1700
Data Index: 3389252 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9121. Min Act: -0.1700
Data Index: 997942 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9121. Min Act: -0.1700
Data Index: 505163 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9121. Min Act: -0.1700
Data Index: 6065652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8496. Min Act: -0.1700
Data Index: 8257978 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8809. Min Act: -0.1700
Data Index: 1534915 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19