Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5772. Min Act: -0.1700
Data Index: 8039236 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.5460. Min Act: -0.1700
Data Index: 5396729 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.4522. Min Act: -0.1700
Data Index: 771232 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.3584. Min Act: -0.1700
Data Index: 8255503 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.2959. Min Act: -0.1700
Data Index: 1719868 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.2647. Min Act: -0.1700
Data Index: 2158721 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.2334. Min Act: -0.1700
Data Index: 1692213 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.2647. Min Act: -0.1700
Data Index: 6695647 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.2647. Min Act: -0.1700
Data Index: 8321134 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.2647. Min Act: -0.1700
Data Index: 6646826 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.2334. Min Act: -0.1700
Data Index: 1447904 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.1709. Min Act: -0.1700
Data Index: 5346596 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.2022. Min Act: -0.1700
Data Index: 4277494 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.2022. Min Act: -0.1700
Data Index: 5396728 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.1709. Min Act: -0.1700
Data Index: 8326358 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.1397. Min Act: -0.1700
Data Index: 2214774 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.1709. Min Act: -0.1700
Data Index: 1170841 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.1397. Min Act: -0.1700
Data Index: 5604066 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.1084. Min Act: -0.1700
Data Index: 6646825 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5772. Min Range: -4.5772
Max Act: 4.1084. Min Act: -0.1700
Data Index: 3721689 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19