Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.6705. Min Act: -0.1700
Data Index: 5400875 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.4932. Min Act: -0.1700
Data Index: 234256 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.4932. Min Act: -0.1700
Data Index: 234259 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.4932. Min Act: -0.1700
Data Index: 234258 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.4770. Min Act: -0.1700
Data Index: 234247 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.4607. Min Act: -0.1700
Data Index: 234248 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.4119. Min Act: -0.1700
Data Index: 4913808 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.4119. Min Act: -0.1700
Data Index: 2340762 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.4119. Min Act: -0.1700
Data Index: 5509785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3956. Min Act: -0.1700
Data Index: 2340761 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3465. Min Act: -0.1700
Data Index: 1076957 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3465. Min Act: -0.1700
Data Index: 3623763 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3629. Min Act: -0.1700
Data Index: 7146142 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3629. Min Act: -0.1700
Data Index: 5508425 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3629. Min Act: -0.1700
Data Index: 1674910 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3301. Min Act: -0.1700
Data Index: 5351378 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3465. Min Act: -0.1700
Data Index: 8431827 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3465. Min Act: -0.1700
Data Index: 8510399 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3137. Min Act: -0.1700
Data Index: 3378276 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6705. Min Range: -2.6705
Max Act: 2.3301. Min Act: -0.1700
Data Index: 6016271 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19