Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.6253. Min Act: -0.1700
Data Index: 436063 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.5315. Min Act: -0.1700
Data Index: 5135005 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.5315. Min Act: -0.1700
Data Index: 7703264 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.5003. Min Act: -0.1700
Data Index: 3109228 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 3416311 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1695
Data Index: 1100929 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 4881727 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 4827601 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 5778647 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 1334092 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 7956552 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 519234 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 2968415 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 5474804 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 7555174 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 2741875 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1699
Data Index: 5314535 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 1577745 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 7069757 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6253. Min Range: -5.6253
Max Act: 5.4690. Min Act: -0.1700
Data Index: 2241697 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19