Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.4337. Min Act: -0.1700
Data Index: 1049445 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.4337. Min Act: -0.1700
Data Index: 1340615 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.4011. Min Act: -0.1700
Data Index: 8604458 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.3684. Min Act: -0.1700
Data Index: 1049447 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.3028. Min Act: -0.1330
Data Index: 4651878 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2863. Min Act: -0.1700
Data Index: 7787617 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2698. Min Act: -0.1431
Data Index: 6313186 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2698. Min Act: -0.1322
Data Index: 5881625 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2698. Min Act: -0.1700
Data Index: 4686289 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2698. Min Act: -0.1700
Data Index: 4967467 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2533. Min Act: -0.1700
Data Index: 4747618 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2533. Min Act: -0.1700
Data Index: 7023655 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2698. Min Act: -0.1700
Data Index: 3148878 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2368. Min Act: -0.1700
Data Index: 1952036 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2203. Min Act: -0.1700
Data Index: 1275713 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2368. Min Act: -0.1700
Data Index: 6652982 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2368. Min Act: -0.1403
Data Index: 7283874 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2368. Min Act: -0.1475
Data Index: 1075720 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2037. Min Act: -0.1556
Data Index: 1241056 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4337. Min Range: -2.4337
Max Act: 2.2203. Min Act: -0.1700
Data Index: 3326049 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19