Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1428 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.6248. Min Act: -0.1700
Data Index: 6431995 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.4060. Min Act: -0.1700
Data Index: 2570558 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.4373. Min Act: -0.1700
Data Index: 7377391 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.4060. Min Act: -0.1700
Data Index: 5799831 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3748. Min Act: -0.1700
Data Index: 5033154 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3435. Min Act: -0.1700
Data Index: 2183679 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3435. Min Act: -0.1700
Data Index: 2741756 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3435. Min Act: -0.1700
Data Index: 3486920 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3435. Min Act: -0.1700
Data Index: 997427 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 1517948 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3123. Min Act: -0.1700
Data Index: 4014051 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3123. Min Act: -0.1700
Data Index: 334354 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3123. Min Act: -0.1700
Data Index: 5861757 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 271928 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 866904 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 1440192 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3123. Min Act: -0.1700
Data Index: 3153489 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 2224016 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2185. Min Act: -0.1700
Data Index: 6278541 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2185. Min Act: -0.1700
Data Index: 724543 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19