Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.5825. Min Act: -0.1700
Data Index: 2114622 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.5200. Min Act: -0.1700
Data Index: 4053078 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.4575. Min Act: -0.1700
Data Index: 5531394 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.4575. Min Act: -0.1700
Data Index: 6190219 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.3950. Min Act: -0.1700
Data Index: 8397731 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.3950. Min Act: -0.1700
Data Index: 3797261 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.3325. Min Act: -0.1700
Data Index: 38943 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.3325. Min Act: -0.1700
Data Index: 4821908 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.3325. Min Act: -0.1700
Data Index: 4278922 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.3325. Min Act: -0.1700
Data Index: 7004221 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.3325. Min Act: -0.1700
Data Index: 1612948 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.3325. Min Act: -0.1700
Data Index: 2506503 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.2700. Min Act: -0.1700
Data Index: 6544243 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.3325. Min Act: -0.1700
Data Index: 5182500 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.2700. Min Act: -0.1700
Data Index: 1180745 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.2700. Min Act: -0.1700
Data Index: 2446514 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.2700. Min Act: -0.1700
Data Index: 7321779 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.2700. Min Act: -0.1700
Data Index: 5856538 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.2700. Min Act: -0.1700
Data Index: 5525483 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5825. Min Range: -7.5825
Max Act: 7.2700. Min Act: -0.1700
Data Index: 8756310 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19