Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1478 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.3522. Min Act: -0.1700
Data Index: 1212765 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.3686. Min Act: -0.1699
Data Index: 1212767 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.3522. Min Act: -0.1700
Data Index: 1212771 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.2700. Min Act: -0.1700
Data Index: 1212772 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.2370. Min Act: -0.1700
Data Index: 1212764 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.2205. Min Act: -0.1700
Data Index: 1212769 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.2205. Min Act: -0.1700
Data Index: 3484394 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.2039. Min Act: -0.1700
Data Index: 913062 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.2039. Min Act: -0.1700
Data Index: 913069 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.1873. Min Act: -0.1699
Data Index: 913063 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.1873. Min Act: -0.1700
Data Index: 3484395 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.1540. Min Act: -0.1700
Data Index: 4833190 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.1373. Min Act: -0.1694
Data Index: 3925963 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.1373. Min Act: -0.1700
Data Index: 6496499 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.1039. Min Act: -0.1700
Data Index: 913059 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.1039. Min Act: -0.1700
Data Index: 4833189 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.0872. Min Act: -0.1700
Data Index: 1212762 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.0704. Min Act: -0.1700
Data Index: 1212763 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.0704. Min Act: -0.1699
Data Index: 6628348 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3686. Min Range: -2.3686
Max Act: 2.0536. Min Act: -0.1700
Data Index: 4658485 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19