Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0448. Min Range: -4.0448
Max Act: 4.0448. Min Act: -0.1700
Data Index: 8585984 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0448. Min Range: -4.0448
Max Act: 4.0136. Min Act: -0.1700
Data Index: 6017155 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0448. Min Range: -4.0448
Max Act: 4.0136. Min Act: -0.1700
Data Index: 4343118 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9823. Min Act: -0.1700
Data Index: 4836135 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9511. Min Act: -0.1700
Data Index: 8371199 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0448. Min Range: -4.0448
Max Act: 4.0136. Min Act: -0.1700
Data Index: 90786 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9823. Min Act: -0.1700
Data Index: 7165275 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9823. Min Act: -0.1700
Data Index: 2992131 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9511. Min Act: -0.1700
Data Index: 2420354 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9511. Min Act: -0.1700
Data Index: 5902904 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9198. Min Act: -0.1700
Data Index: 3813397 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9511. Min Act: -0.1700
Data Index: 553521 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9198. Min Act: -0.1700
Data Index: 3014753 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9198. Min Act: -0.1700
Data Index: 8725944 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.9511. Min Act: -0.1700
Data Index: 5607951 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.8885. Min Act: -0.1700
Data Index: 7069687 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.8885. Min Act: -0.1700
Data Index: 4126341 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.8573. Min Act: -0.1700
Data Index: 5292133 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.8573. Min Act: -0.1700
Data Index: 8166051 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0448. Min Range: -4.0448
Max Act: 3.8885. Min Act: -0.1700
Data Index: 7664313 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19