Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4323 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.4278. Min Act: -0.1700
Data Index: 4449589 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.2552. Min Act: -0.1700
Data Index: 1335884 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.2238. Min Act: -0.1700
Data Index: 2155091 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.2081. Min Act: -0.1700
Data Index: 4568581 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.1924. Min Act: -0.1700
Data Index: 575417 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.1294. Min Act: -0.1700
Data Index: 4807489 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.0979. Min Act: -0.1700
Data Index: 3516948 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.0664. Min Act: -0.1700
Data Index: 2666774 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.0664. Min Act: -0.1700
Data Index: 5261434 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.0506. Min Act: -0.1700
Data Index: 1769647 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.0190. Min Act: -0.1700
Data Index: 3410673 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.0032. Min Act: -0.1700
Data Index: 8216600 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.0190. Min Act: -0.1700
Data Index: 7260688 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.0190. Min Act: -0.1700
Data Index: 6550266 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4278. Min Range: -3.4278
Max Act: 3.0190. Min Act: -0.1700
Data Index: 1789744 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4278. Min Range: -3.4278
Max Act: 2.9874. Min Act: -0.1700
Data Index: 8200830 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4278. Min Range: -3.4278
Max Act: 2.9874. Min Act: -0.1700
Data Index: 8443376 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4278. Min Range: -3.4278
Max Act: 2.9716. Min Act: -0.1700
Data Index: 7226249 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4278. Min Range: -3.4278
Max Act: 2.9716. Min Act: -0.1700
Data Index: 6372268 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4278. Min Range: -3.4278
Max Act: 2.9874. Min Act: -0.1700
Data Index: 6073158 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19