Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5969 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.6204. Min Act: -0.1700
Data Index: 2302286 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.5578. Min Act: -0.1700
Data Index: 2477944 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.5421. Min Act: -0.1700
Data Index: 3264440 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.4951. Min Act: -0.1700
Data Index: 8320558 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3854. Min Act: -0.1700
Data Index: 2237054 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3854. Min Act: -0.1700
Data Index: 4098275 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3541. Min Act: -0.1700
Data Index: 3058921 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3227. Min Act: -0.1700
Data Index: 1280171 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3384. Min Act: -0.1700
Data Index: 3665693 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3384. Min Act: -0.1700
Data Index: 6994548 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3384. Min Act: -0.1700
Data Index: 227336 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3227. Min Act: -0.1700
Data Index: 2114131 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3384. Min Act: -0.1700
Data Index: 5143742 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.2913. Min Act: -0.1700
Data Index: 981572 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3070. Min Act: -0.1700
Data Index: 4146441 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3070. Min Act: -0.1700
Data Index: 8254522 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3070. Min Act: -0.1700
Data Index: 218967 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.3070. Min Act: -0.1700
Data Index: 6697088 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.2913. Min Act: -0.1700
Data Index: 5003213 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6204. Min Range: -3.6204
Max Act: 3.2913. Min Act: -0.1700
Data Index: 1198335 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19