Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 892 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.5316. Min Act: -0.1700
Data Index: 4834044 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.5160. Min Act: -0.1700
Data Index: 687797 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.4376. Min Act: -0.1700
Data Index: 2571236 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.4063. Min Act: -0.1700
Data Index: 6043137 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2965. Min Act: -0.1700
Data Index: 5083505 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.3592. Min Act: -0.1700
Data Index: 1007801 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.3279. Min Act: -0.1700
Data Index: 5978259 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2651. Min Act: -0.1700
Data Index: 8547359 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2808. Min Act: -0.1700
Data Index: 7626539 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2808. Min Act: -0.1700
Data Index: 8369521 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2494. Min Act: -0.1700
Data Index: 8825896 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2336. Min Act: -0.1700
Data Index: 783725 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2336. Min Act: -0.1700
Data Index: 1071047 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2336. Min Act: -0.1700
Data Index: 1190517 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2336. Min Act: -0.1700
Data Index: 4489782 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2179. Min Act: -0.1700
Data Index: 1285276 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2022. Min Act: -0.1700
Data Index: 447089 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2022. Min Act: -0.1700
Data Index: 8664789 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.1865. Min Act: -0.1700
Data Index: 3933245 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5316. Min Range: -3.5316
Max Act: 3.2022. Min Act: -0.1694
Data Index: 2453213 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19