Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1473 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3208. Min Range: -4.3208
Max Act: 4.3208. Min Act: -0.1700
Data Index: 3779033 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3208. Min Range: -4.3208
Max Act: 4.1020. Min Act: -0.1700
Data Index: 495383 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3208. Min Range: -4.3208
Max Act: 4.1020. Min Act: -0.1700
Data Index: 1967131 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3208. Min Range: -4.3208
Max Act: 4.0707. Min Act: -0.1700
Data Index: 6726680 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3208. Min Range: -4.3208
Max Act: 4.0395. Min Act: -0.1700
Data Index: 2539612 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3208. Min Range: -4.3208
Max Act: 4.0395. Min Act: -0.1700
Data Index: 1813546 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3208. Min Range: -4.3208
Max Act: 4.0238. Min Act: -0.1700
Data Index: 6755958 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3208. Min Range: -4.3208
Max Act: 4.0082. Min Act: -0.1700
Data Index: 241823 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.9926. Min Act: -0.1700
Data Index: 4308821 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.9457. Min Act: -0.1700
Data Index: 5019900 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.9769. Min Act: -0.1700
Data Index: 2483945 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.9300. Min Act: -0.1700
Data Index: 7565765 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.9144. Min Act: -0.1700
Data Index: 2890436 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.9144. Min Act: -0.1700
Data Index: 268918 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.9144. Min Act: -0.1700
Data Index: 7101651 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.9300. Min Act: -0.1700
Data Index: 4459394 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.9300. Min Act: -0.1700
Data Index: 5602052 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.8988. Min Act: -0.1700
Data Index: 8490902 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.8988. Min Act: -0.1700
Data Index: 455629 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3208. Min Range: -4.3208
Max Act: 3.8831. Min Act: -0.1700
Data Index: 7379685 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19