Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 396 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.5839. Min Act: -0.1700
Data Index: 5157238 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.5214. Min Act: -0.1700
Data Index: 5959387 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.4276. Min Act: -0.1700
Data Index: 6159878 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.4589. Min Act: -0.1700
Data Index: 8396423 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.4589. Min Act: -0.1700
Data Index: 3093533 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.4589. Min Act: -0.1700
Data Index: 4424831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3964. Min Act: -0.1700
Data Index: 407778 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3964. Min Act: -0.1700
Data Index: 8415323 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3651. Min Act: -0.1700
Data Index: 8792051 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3964. Min Act: -0.1700
Data Index: 405407 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3339. Min Act: -0.1700
Data Index: 7328046 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3339. Min Act: -0.1700
Data Index: 587600 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3026. Min Act: -0.1700
Data Index: 5905518 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3339. Min Act: -0.1700
Data Index: 2006193 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3026. Min Act: -0.1700
Data Index: 3345858 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.3026. Min Act: -0.1700
Data Index: 1371689 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.2401. Min Act: -0.1700
Data Index: 1097977 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.2713. Min Act: -0.1700
Data Index: 546621 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.2713. Min Act: -0.1700
Data Index: 4918680 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5839. Min Range: -4.5839
Max Act: 4.2713. Min Act: -0.1700
Data Index: 4966203 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19