Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.3006. Min Act: -0.1700
Data Index: 2609624 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.2693. Min Act: -0.1700
Data Index: 7290067 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.2068. Min Act: -0.1700
Data Index: 7591085 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.2380. Min Act: -0.1700
Data Index: 5759539 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.2380. Min Act: -0.1700
Data Index: 5695389 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.2068. Min Act: -0.1700
Data Index: 6585135 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.1755. Min Act: -0.1700
Data Index: 6878509 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.1755. Min Act: -0.1700
Data Index: 3308996 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.1443. Min Act: -0.1700
Data Index: 1565690 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.1443. Min Act: -0.1700
Data Index: 6610141 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.1443. Min Act: -0.1700
Data Index: 1071772 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.1443. Min Act: -0.1700
Data Index: 8062830 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.1130. Min Act: -0.1700
Data Index: 4468597 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.1130. Min Act: -0.1700
Data Index: 4633481 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.0818. Min Act: -0.1700
Data Index: 7008293 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.0818. Min Act: -0.1700
Data Index: 1585961 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.0818. Min Act: -0.1700
Data Index: 538245 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.0818. Min Act: -0.1700
Data Index: 3894596 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.0818. Min Act: -0.1700
Data Index: 156035 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3006. Min Range: -4.3006
Max Act: 4.0818. Min Act: -0.1700
Data Index: 6470124 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19