Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.2765. Min Act: -0.1700
Data Index: 1726104 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.2451. Min Act: -0.1700
Data Index: 8002626 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.2451. Min Act: -0.1700
Data Index: 3547262 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.2451. Min Act: -0.1700
Data Index: 3742746 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.2137. Min Act: -0.1700
Data Index: 4291948 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.2137. Min Act: -0.1700
Data Index: 4625939 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.2137. Min Act: -0.1700
Data Index: 1726103 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.2137. Min Act: -0.1700
Data Index: 4045627 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.2137. Min Act: -0.1700
Data Index: 8135655 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 3953045 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 3762688 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 3692744 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 805360 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 1323545 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 4771116 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 1510215 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 5135612 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 5142421 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 5378182 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2765. Min Range: -3.2765
Max Act: 3.1822. Min Act: -0.1700
Data Index: 6800720 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19