Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.3179. Min Act: -0.1700
Data Index: 6807469 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2827. Min Act: -0.1655
Data Index: 5551977 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2650. Min Act: -0.1700
Data Index: 4048484 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2650. Min Act: -0.1700
Data Index: 324320 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2562. Min Act: -0.1697
Data Index: 1679950 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2474. Min Act: -0.1700
Data Index: 8172545 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2386. Min Act: -0.1699
Data Index: 7223616 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2209. Min Act: -0.1699
Data Index: 7626543 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2209. Min Act: -0.1700
Data Index: 7977192 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2209. Min Act: -0.1700
Data Index: 4786791 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2121. Min Act: -0.1700
Data Index: 4307470 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.1945. Min Act: -0.1600
Data Index: 201114 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.2033. Min Act: -0.1696
Data Index: 7969815 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.1769. Min Act: -0.1700
Data Index: 6289515 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.1769. Min Act: -0.1699
Data Index: 6744654 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.1769. Min Act: -0.1700
Data Index: 4982339 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.1769. Min Act: -0.1700
Data Index: 5839004 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.1681. Min Act: -0.1699
Data Index: 998108 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.1681. Min Act: -0.1700
Data Index: 4119171 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3179. Min Range: -1.3179
Max Act: 1.1681. Min Act: -0.1700
Data Index: 1379861 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19