Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1542 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3273. Min Range: -8.3273
Max Act: 8.3273. Min Act: -0.1700
Data Index: 3514276 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3273. Min Range: -8.3273
Max Act: 8.2648. Min Act: -0.1699
Data Index: 5695439 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3273. Min Range: -8.3273
Max Act: 8.0773. Min Act: -0.1700
Data Index: 8397915 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3273. Min Range: -8.3273
Max Act: 8.0148. Min Act: -0.1700
Data Index: 1648198 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3273. Min Range: -8.3273
Max Act: 8.0148. Min Act: -0.1700
Data Index: 4228785 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.9523. Min Act: -0.1700
Data Index: 7798643 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.8585. Min Act: -0.1700
Data Index: 2875674 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.8585. Min Act: -0.1700
Data Index: 5176122 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.8273. Min Act: -0.1700
Data Index: 2592025 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.7960. Min Act: -0.1700
Data Index: 5760774 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.7335. Min Act: -0.1700
Data Index: 8701249 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.7335. Min Act: -0.1700
Data Index: 4137002 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.7335. Min Act: -0.1700
Data Index: 5038086 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.7023. Min Act: -0.1699
Data Index: 6177923 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.6085. Min Act: -0.1700
Data Index: 7400376 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.6398. Min Act: -0.1700
Data Index: 6118193 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.6085. Min Act: -0.1700
Data Index: 5842076 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.5773. Min Act: -0.1700
Data Index: 1740321 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.5773. Min Act: -0.1700
Data Index: 8231242 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3273. Min Range: -8.3273
Max Act: 7.5148. Min Act: -0.1700
Data Index: 3058795 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19