Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.8627. Min Act: -0.1700
Data Index: 840798 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.8370. Min Act: -0.1700
Data Index: 28336 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.8027. Min Act: -0.1699
Data Index: 7468611 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7769. Min Act: -0.1700
Data Index: 5750376 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7682. Min Act: -0.1700
Data Index: 8495312 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7682. Min Act: -0.1700
Data Index: 908612 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7510. Min Act: -0.1700
Data Index: 2868557 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7510. Min Act: -0.1700
Data Index: 890177 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7510. Min Act: -0.1700
Data Index: 2956602 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7423. Min Act: -0.1700
Data Index: 4209215 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7510. Min Act: -0.1700
Data Index: 3850448 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7423. Min Act: -0.1700
Data Index: 6322050 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7423. Min Act: -0.1700
Data Index: 1633615 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7423. Min Act: -0.1700
Data Index: 6512937 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7423. Min Act: -0.1700
Data Index: 7910133 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7250. Min Act: -0.1700
Data Index: 4584860 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7250. Min Act: -0.1700
Data Index: 7199555 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7337. Min Act: -0.1700
Data Index: 8162467 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7337. Min Act: -0.1700
Data Index: 500071 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8627. Min Range: -1.8627
Max Act: 1.7337. Min Act: -0.1700
Data Index: 6256034 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19