Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4289. Min Range: -5.4289
Max Act: 5.4289. Min Act: -0.1700
Data Index: 5538648 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4289. Min Range: -5.4289
Max Act: 5.2102. Min Act: -0.1700
Data Index: 8706968 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4289. Min Range: -5.4289
Max Act: 5.1789. Min Act: -0.1700
Data Index: 719515 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4289. Min Range: -5.4289
Max Act: 5.1477. Min Act: -0.1700
Data Index: 2636082 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4289. Min Range: -5.4289
Max Act: 5.1477. Min Act: -0.1700
Data Index: 3801282 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4289. Min Range: -5.4289
Max Act: 5.1477. Min Act: -0.1700
Data Index: 624828 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4289. Min Range: -5.4289
Max Act: 5.0227. Min Act: -0.1700
Data Index: 3416418 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4289. Min Range: -5.4289
Max Act: 5.0227. Min Act: -0.1700
Data Index: 4064914 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.9602. Min Act: -0.1700
Data Index: 141459 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4289. Min Range: -5.4289
Max Act: 5.0227. Min Act: -0.1700
Data Index: 8246948 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.9914. Min Act: -0.1700
Data Index: 3871328 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.9602. Min Act: -0.1700
Data Index: 6431257 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.9602. Min Act: -0.1700
Data Index: 921293 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.9289. Min Act: -0.1700
Data Index: 8320677 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.8977. Min Act: -0.1700
Data Index: 1792945 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.8664. Min Act: -0.1700
Data Index: 2878802 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.9602. Min Act: -0.1700
Data Index: 982171 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.8977. Min Act: -0.1700
Data Index: 46975 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.8977. Min Act: -0.1700
Data Index: 4731956 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4289. Min Range: -5.4289
Max Act: 4.9289. Min Act: -0.1700
Data Index: 403796 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19