Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1805 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.2222. Min Act: -0.1700
Data Index: 8576187 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.1593. Min Act: -0.1700
Data Index: 5140304 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.1593. Min Act: -0.1700
Data Index: 7516061 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.1436. Min Act: -0.1700
Data Index: 7161954 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.1121. Min Act: -0.1700
Data Index: 6261347 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.1121. Min Act: -0.1700
Data Index: 4270237 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.1121. Min Act: -0.1700
Data Index: 2705389 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.1278. Min Act: -0.1700
Data Index: 3613538 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0963. Min Act: -0.1700
Data Index: 8653117 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.1121. Min Act: -0.1700
Data Index: 6662346 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0963. Min Act: -0.1700
Data Index: 6217567 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0805. Min Act: -0.1700
Data Index: 713294 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0805. Min Act: -0.1700
Data Index: 2162462 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0963. Min Act: -0.1700
Data Index: 2154022 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0805. Min Act: -0.1700
Data Index: 3414821 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0648. Min Act: -0.1700
Data Index: 4684543 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0490. Min Act: -0.1700
Data Index: 7717716 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0490. Min Act: -0.1700
Data Index: 5793026 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0648. Min Act: -0.1700
Data Index: 1439520 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2222. Min Range: -3.2222
Max Act: 3.0490. Min Act: -0.1700
Data Index: 1570815 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19