Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2434 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1263. Min Range: -8.1263
Max Act: 8.1263. Min Act: -0.1700
Data Index: 6111638 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1263. Min Range: -8.1263
Max Act: 8.0950. Min Act: -0.1700
Data Index: 8150148 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.9388. Min Act: -0.1700
Data Index: 6789147 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.8763. Min Act: -0.1700
Data Index: 6330051 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.8763. Min Act: -0.1700
Data Index: 6070383 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.8450. Min Act: -0.1700
Data Index: 5227409 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.6888. Min Act: -0.1700
Data Index: 4941081 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.6263. Min Act: -0.1700
Data Index: 7678145 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.5950. Min Act: -0.1700
Data Index: 4723682 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.5325. Min Act: -0.1700
Data Index: 7650453 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.4700. Min Act: -0.1700
Data Index: 1989642 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.4075. Min Act: -0.1700
Data Index: 8768880 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.3450. Min Act: -0.1700
Data Index: 7340240 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.3763. Min Act: -0.1700
Data Index: 3932141 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.2825. Min Act: -0.1700
Data Index: 5784056 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.2825. Min Act: -0.1700
Data Index: 768515 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.3138. Min Act: -0.1700
Data Index: 4657121 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.2825. Min Act: -0.1700
Data Index: 8748056 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.2513. Min Act: -0.1700
Data Index: 8421818 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1263. Min Range: -8.1263
Max Act: 7.2513. Min Act: -0.1700
Data Index: 1684401 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19