Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5605 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.6197. Min Act: -0.1700
Data Index: 3072377 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.5259. Min Act: -0.1700
Data Index: 6005302 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4947. Min Act: -0.1700
Data Index: 8318936 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.4009. Min Act: -0.1700
Data Index: 4664841 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3384. Min Act: -0.1700
Data Index: 5613189 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3384. Min Act: -0.1700
Data Index: 4143327 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 3422003 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 4737512 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.3072. Min Act: -0.1700
Data Index: 4699591 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.2134. Min Act: -0.1700
Data Index: 3427326 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.2134. Min Act: -0.1700
Data Index: 6987136 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.2134. Min Act: -0.1700
Data Index: 1471386 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.1822. Min Act: -0.1700
Data Index: 4443960 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.1509. Min Act: -0.1700
Data Index: 4684172 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.1197. Min Act: -0.1700
Data Index: 4473348 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.1197. Min Act: -0.1700
Data Index: 1365914 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.1197. Min Act: -0.1700
Data Index: 3107270 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.0884. Min Act: -0.1700
Data Index: 8145490 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.0884. Min Act: -0.1700
Data Index: 5244844 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6197. Min Range: -5.6197
Max Act: 5.0572. Min Act: -0.1700
Data Index: 2644017 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19