Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2683 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7833. Min Act: -0.1700
Data Index: 5091632 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7833. Min Act: -0.1700
Data Index: 2999673 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7520. Min Act: -0.1700
Data Index: 3961106 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 6541044 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7520. Min Act: -0.1700
Data Index: 6161325 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 4564949 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 32663 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7520. Min Act: -0.1700
Data Index: 855944 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 4178089 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7520. Min Act: -0.1700
Data Index: 79811 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 4115518 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7520. Min Act: -0.1700
Data Index: 1639659 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 3071963 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7520. Min Act: -0.1700
Data Index: 3071961 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 592184 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 2474967 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 2206027 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 1816590 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 1795271 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7833. Min Range: -4.7833
Max Act: 4.7208. Min Act: -0.1700
Data Index: 286308 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19