Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.3352. Min Act: -0.1700
Data Index: 446035 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.2414. Min Act: -0.1700
Data Index: 2094211 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.1164. Min Act: -0.1700
Data Index: 3511094 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.0227. Min Act: -0.1700
Data Index: 4365707 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.9914. Min Act: -0.1700
Data Index: 1655849 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.9602. Min Act: -0.1700
Data Index: 3320423 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.9289. Min Act: -0.1700
Data Index: 4256611 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.9289. Min Act: -0.1700
Data Index: 1379167 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8977. Min Act: -0.1700
Data Index: 1376105 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8664. Min Act: -0.1700
Data Index: 4659488 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8664. Min Act: -0.1700
Data Index: 6748638 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8664. Min Act: -0.1700
Data Index: 8182764 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8977. Min Act: -0.1700
Data Index: 4683285 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8352. Min Act: -0.1700
Data Index: 3454192 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8664. Min Act: -0.1700
Data Index: 8314115 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8352. Min Act: -0.1700
Data Index: 986408 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8352. Min Act: -0.1700
Data Index: 5105755 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8039. Min Act: -0.1700
Data Index: 4643159 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8039. Min Act: -0.1700
Data Index: 6221972 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8039. Min Act: -0.1700
Data Index: 5450967 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19