Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.3776. Min Act: -0.1700
Data Index: 7250791 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.3464. Min Act: -0.1700
Data Index: 2418802 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.2839. Min Act: -0.1700
Data Index: 5566701 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.2839. Min Act: -0.1700
Data Index: 4295141 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.2526. Min Act: -0.1700
Data Index: 7038570 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.2526. Min Act: -0.1700
Data Index: 1849435 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.2214. Min Act: -0.1700
Data Index: 2098872 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.2214. Min Act: -0.1700
Data Index: 4052420 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.2214. Min Act: -0.1700
Data Index: 3756694 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.2214. Min Act: -0.1700
Data Index: 4052421 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.2214. Min Act: -0.1700
Data Index: 3756693 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.1901. Min Act: -0.1700
Data Index: 6682622 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.1901. Min Act: -0.1700
Data Index: 2999481 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.1589. Min Act: -0.1700
Data Index: 6810709 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.1589. Min Act: -0.1700
Data Index: 2098871 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.1589. Min Act: -0.1700
Data Index: 3756695 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.1589. Min Act: -0.1700
Data Index: 7361347 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.1276. Min Act: -0.1700
Data Index: 3573494 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.1276. Min Act: -0.1700
Data Index: 2999482 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3776. Min Range: -5.3776
Max Act: 5.1276. Min Act: -0.1700
Data Index: 2201955 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19